© 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. 34-GEMMASCOPE-RES-131K
    7. 31104
    Prev
    Next
    INDEX
    Explanations

    forceful physical actions

    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_34/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
     Comisión
    -0.84
    ниципа
    -0.81
    ारी
    -0.81
    ALTH
    -0.81
    جا
    -0.80
    tahui
    -0.80
    orient
    -0.80
    어
    -0.79
    Buffer
    -0.79
    arat
    -0.79
    POSITIVE LOGITS
     away
    1.79
     holes
    1.73
     into
    1.42
     the
    1.26
     against
    1.23
     out
    1.22
     up
    1.19
     through
    1.17
     chunks
    1.13
    holes
    1.05
    Activations Density 0.034%

    No Known Activations