© 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. 72683
    Prev
    Next
    INDEX
    Explanations

    hosting both

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

    The neuron activates on numeric measurements and related statistical data (e.g. weather highs, scores, odds).

    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
     algunos
    -1.21
    可能
    -1.16
    不断
    -1.15
    隽
    -1.13
     (!__
    -1.13
     różnych
    -1.13
     pueden
    -1.09
    ないように
    -1.09
    してない
    -1.09
     Some
    -1.09
    POSITIVE LOGITS
    ditionally
    1.21
     kado
    1.18
     XXVII
    1.13
     lasci
    1.12
     kalender
    1.10
     minne
    1.09
     just
    1.08
     utop
    1.08
     tradis
    1.07
    fore
    1.06
    Activations Density 0.034%

    No Known Activations