© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49659
    Prev
    Next
    INDEX
    Explanations

    go to or toward

    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
     and
    -0.81
     étui
    -0.80
    vode
    -0.80
    原创
    -0.77
    KEYCODE
    -0.77
    付けた
    -0.77
    yska
    -0.76
    เข
    -0.76
     Geek
    -0.76
     rozgry
    -0.76
    POSITIVE LOGITS
     to
    1.34
     towards
    1.20
     toward
    1.02
     directly
    0.95
     into
    0.89
    specified
    0.85
    Etat
    0.83
     straight
    0.82
    used
    0.77
    Specified
    0.77
    Activations Density 0.013%

    No Known Activations