© 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. 76173
    Prev
    Next
    INDEX
    Explanations

    Alcohol, Tobacco, Secretary, decision

    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
     sentences
    -0.71
     handle
    -0.69
    WRITE
    -0.68
     minds
    -0.68
    Mech
    -0.68
     Satz
    -0.67
     phrases
    -0.65
    tamientos
    -0.65
    enschaften
    -0.65
     writings
    -0.64
    POSITIVE LOGITS
    lur
    0.72
    pende
    0.68
    飲
    0.67
    input
    0.66
     Torque
    0.65
    lanti
    0.64
    тация
    0.63
    ⁍
    0.63
    输入
    0.61
    lerinin
    0.61
    Activations Density 0.084%

    No Known Activations