© 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. 103085
    Prev
    Next
    INDEX
    Explanations

    Q: content

    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
    providedIn
    -0.86
     vya
    -0.85
     selepas
    -0.80
    essége
    -0.76
    Soon
    -0.76
    New
    -0.75
    VT
    -0.74
     Garn
    -0.74
    Extension
    -0.73
    شل
    -0.73
    POSITIVE LOGITS
    carrinho
    0.89
     patching
    0.85
    Baylor
    0.84
    bmw
    0.82
    avantage
    0.81
    Baj
    0.81
    nomin
    0.79
    Préparation
    0.79
    Hoa
    0.78
    Mature
    0.78
    Activations Density 0.000%

    No Known Activations