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. 8943
    Prev
    Next
    INDEX
    Explanations

    websites and links

    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
    rent
    -0.74
    ęk
    -0.70
    animate
    -0.68
    熏
    -0.68
     Byrne
    -0.67
    JsonProperty
    -0.66
    Coy
    -0.66
    附加
    -0.66
     Aar
    -0.65
    tween
    -0.65
    POSITIVE LOGITS
     untersch
    0.70
    nikiem
    0.68
     Protestant
    0.67
    posx
    0.67
     Irishman
    0.67
    lectric
    0.66
    ummer
    0.66
    atibility
    0.66
     Aftermath
    0.66
    batman
    0.65
    Activations Density 0.064%

    No Known Activations