© 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. 50165
    Prev
    Next
    INDEX
    Explanations

    activities or states

    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
    romas
    -1.13
     selaku
    -1.01
    成為
    -1.00
     etching
    -0.96
    Surprisingly
    -0.94
     vostre
    -0.94
    ﾕ
    -0.94
     morgan
    -0.93
     TÉCNICA
    -0.93
    ቼ
    -0.91
    POSITIVE LOGITS
    redient
    0.99
     mindful
    0.97
     creando
    0.94
    ри
    0.93
    考えて
    0.92
     considerando
    0.91
     острова
    0.90
    capacidad
    0.90
    tvb
    0.89
    gmd
    0.89
    Activations Density 0.109%

    No Known Activations