© 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. 34300
    Prev
    Next
    INDEX
    Explanations

    can be

    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
    l
    -0.92
    e
    -0.90
    the
    -0.90
    🤯
    -0.90
     pouvoir
    -0.89
    能在
    -0.88
    d
    -0.88
    Figs
    -0.86
     Может
    -0.85
    IVATE
    -0.85
    POSITIVE LOGITS
     you
    2.06
     your
    1.45
    corrhi
    1.11
     budete
    1.09
     daunting
    1.08
    楂
    1.05
     sonra
    1.05
    ＊＊＊
    1.05
     invloed
    1.05
     YOU
    1.04
    Activations Density 0.096%

    No Known Activations