© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15774
    Prev
    Next
    INDEX
    Explanations

    ortho fries rearrangement

    np_acts-logits-general · gemini-2.5-flash-lite

    captions, labels, or descriptions that accompany scientific figures, charts, or images.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects figure captions or other labeled diagram/figure headings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IRUS
    -1.23
    Siapa
    -1.16
    rą
    -1.13
    轳
    -1.13
    Quais
    -1.13
    )$,
    -1.09
    亠
    -1.09
    ActionCreators
    -1.05
    そういえば
    -1.05
     what
    -1.05
    POSITIVE LOGITS
    </em>
    1.20
     Muzeum
    1.16
     hinzufügen
    1.16
    </i>
    1.14
     pictured
    1.13
     despues
    1.08
     stück
    1.08
    ecause
    1.08
    efore
    1.07
    prnewswire
    1.06
    Activations Density 0.064%

    No Known Activations