© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45456
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

    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
     biochemical
    -0.74
    水
    -0.74
     Proc
    -0.71
    znam
    -0.66
    Sh
    -0.66
     $,
    -0.66
    خب
    -0.66
     Replace
    -0.65
     水
    -0.65
     treated
    -0.64
    POSITIVE LOGITS
    ramas
    0.79
     surround
    0.73
     Carrot
    0.70
     barked
    0.68
     kel
    0.67
    ◀
    0.66
     bornes
    0.66
     Conductor
    0.66
     jewelry
    0.65
    skiego
    0.65
    Activations Density 0.072%

    No Known Activations