Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8938
    Prev
    Next
    INDEX
    Explanations

    LEED certification, assembly, HTML title, color scheme

    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
     HID
    -0.69
    meida
    -0.68
     intermitt
    -0.66
     XT
    -0.65
    理由
    -0.65
     landed
    -0.64
     missp
    -0.64
     rescues
    -0.64
    hii
    -0.63
    ラン
    -0.63
    POSITIVE LOGITS
     Coord
    0.69
     profit
    0.69
    Playback
    0.68
     Acres
    0.66
     mirror
    0.66
     SERIES
    0.65
     מר
    0.64
    Videos
    0.64
     reservation
    0.63
     Sick
    0.63
    Activations Density 0.080%

    No Known Activations