© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118819
    Prev
    Next
    INDEX
    Explanations

    script and embedded code

    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
    keith
    -0.70
    Mexico
    -0.70
    SessionId
    -0.69
     folyam
    -0.66
     István
    -0.66
    竊
    -0.65
    marc
    -0.65
     Electra
    -0.65
    णा
    -0.65
    igsaw
    -0.65
    POSITIVE LOGITS
    Welfare
    0.81
    standes
    0.74
    tikai
    0.68
     compare
    0.66
    toch
    0.64
     bene
    0.63
     душ
    0.63
     licenses
    0.61
    较
    0.60
     keadaan
    0.60
    Activations Density 0.050%

    No Known Activations