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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80748
    Prev
    Next
    INDEX
    Explanations

    alpha followed by something

    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
    '
    -0.93
    流れ
    -0.91
     -
    -0.83
    bu
    -0.78
     it
    -0.78
    这让
    -0.77
    tions
    -0.76
     enough
    -0.75
     antecedents
    -0.75
    POSITIVE LOGITS
    betic
    1.33
    betical
    1.30
    alpha
    1.07
    Alpha
    1.05
    בית
    1.03
     kelime
    1.01
    ριθ
    0.95
     ")");
    0.95
    retta
    0.94
     Alpha
    0.93
    Activations Density 0.046%

    No Known Activations