© 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. 73280
    Prev
    Next
    INDEX
    Explanations

    connects to

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

    The neuron is triggered by numeric tokens (i.e. numbers and measurements).

    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
     alignItems
    -1.16
     Российской
    -1.05
     marginLeft
    -1.05
    ÿ
    -1.05
     marginTop
    -1.02
     composants
    -1.02
     estando
    -0.99
    niti
    -0.98
    ราะ
    -0.95
     justifyContent
    -0.95
    POSITIVE LOGITS
     another
    1.34
     the
    1.31
     every
    1.19
     from
    1.14
     with
    1.13
     each
    1.08
     your
    1.07
     various
    0.96
     inapropiados
    0.95
     both
    0.94
    Activations Density 0.087%

    No Known Activations