© 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. 33063
    Prev
    Next
    INDEX
    Explanations

    abstract states and concepts

    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
     />';
    -1.38
    為に
    -1.34
    étaient
    -1.26
     to
    -1.16
     españoles
    -1.16
    ૦
    -1.15
     vollkommen
    -1.14
    犼
    -1.11
    ことから
    -1.11
     europeos
    -1.10
    POSITIVE LOGITS
     should
    1.71
     is
    1.62
     can
    1.57
     shouldn
    1.39
     must
    1.37
     cannot
    1.34
     sometimes
    1.34
     certainly
    1.30
     are
    1.28
     surely
    1.27
    Activations Density 0.030%

    No Known Activations