© 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. 107874
    Prev
    Next
    INDEX
    Explanations

    pressing against

    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
    seurs
    -0.82
    outed
    -0.81
    Nearby
    -0.77
    QLabel
    -0.73
     Kirsch
    -0.72
    museum
    -0.69
    相關
    -0.68
    FromJson
    -0.67
     Fink
    -0.67
     cuerda
    -0.67
    POSITIVE LOGITS
     against
    3.47
    against
    2.41
    Against
    2.36
     Against
    2.31
     touching
    1.72
     pressed
    1.71
     AGAINST
    1.63
     sát
    1.55
     close
    1.55
     tegen
    1.46
    Activations Density 0.100%

    No Known Activations