© 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. 33968
    Prev
    Next
    INDEX
    Explanations

    lists, numbers, and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    कर
    -1.15
    -1.13
     even
    -1.10
     पर
    -1.06
     на
    -1.05
    は
    -1.04
    👲
    -1.03
     also
    -1.02
     often
    -1.00
     became
    -1.00
    POSITIVE LOGITS
    ところに
    1.32
    を越
    1.18
    えました
    1.13
     пришли
    1.12
    ものが
    1.10
    優しく
    1.09
     travailler
    1.09
    瞠
    1.08
     magnificent
    1.05
     görünt
    1.05
    Activations Density 0.085%

    No Known Activations