© 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. 58845
    Prev
    Next
    INDEX
    Explanations

    technical terms and 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
    isert
    -0.82
     gardien
    -0.80
     wakati
    -0.78
    plaat
    -0.78
    >');
    -0.77
     punta
    -0.75
    Occupied
    -0.75
    Carlton
    -0.73
    .~(\
    -0.73
    servicios
    -0.73
    POSITIVE LOGITS
    الثة
    0.83
    classID
    0.80
    雯
    0.78
    𝔠
    0.78
     undersø
    0.75
    懣
    0.74
    Basically
    0.74
     абсолютно
    0.73
    usually
    0.73
     Prototype
    0.72
    Activations Density 0.148%

    No Known Activations