© 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. 34742
    Prev
    Next
    INDEX
    Explanations

    css and js file paths

    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
    R
    -1.02
    N
    -1.00
    W
    -1.00
    V
    -0.96
    X
    -0.93
     To
    -0.92
     Even
    -0.92
    S
    -0.91
    Y
    -0.91
    NO
    -0.91
    POSITIVE LOGITS
     rigide
    1.20
     maïs
    1.12
     multicolore
    1.10
    を活用
    1.10
     konflik
    1.09
     spontan
    1.07
     musée
    1.06
    プリング
    1.04
    もちゃ
    1.04
    ριο
    1.03
    Activations Density 0.008%

    No Known Activations