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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99925
    Prev
    Next
    INDEX
    Explanations

    apache

    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
    лакти
    -0.85
    zzlies
    -0.84
     cocaína
    -0.82
    ABILIDAD
    -0.81
    창
    -0.80
    GeneratedValue
    -0.80
    BED
    -0.80
    丢
    -0.79
    ciatore
    -0.79
    푹
    -0.79
    POSITIVE LOGITS
     eterno
    0.77
     handleChange
    0.77
     nobis
    0.76
    涅
    0.75
    によっては
    0.75
     саду
    0.75
     Fotograf
    0.73
     speciali
    0.71
    ственные
    0.70
     sacco
    0.70
    Activations Density 0.000%

    No Known Activations