© 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. 109655
    Prev
    Next
    INDEX
    Explanations

    XML namespace prefix mc

    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
    @
    -0.96
    <h2>
    -0.93
    -@
    -0.84
    fano
    -0.82
     @
    -0.81
    ...@
    -0.80
     from
    -0.80
    Young
    -0.80
    ,@
    -0.80
    ∛
    -0.79
    POSITIVE LOGITS
    Aerop
    1.07
     Situationen
    1.05
    Giraffe
    1.04
    Trish
    1.03
    ܣ
    0.98
    Proble
    0.95
    を生
    0.94
    Checklist
    0.94
    Jennie
    0.93
    Curs
    0.91
    Activations Density 0.000%

    No Known Activations