© 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. 103874
    Prev
    Next
    INDEX
    Explanations

    file paths with var or www

    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
    ṓ
    -0.89
     wrongs
    -0.82
     Yojana
    -0.81
    retts
    -0.78
    难
    -0.76
    kA
    -0.75
    IRAN
    -0.75
     翔
    -0.72
    따
    -0.72
     часа
    -0.71
    POSITIVE LOGITS
     Heilige
    0.82
    囮
    0.79
    tura
    0.78
     PLWABN
    0.78
    urfs
    0.77
     badan
    0.76
    outcome
    0.75
    rugu
    0.75
     benutzt
    0.75
     reis
    0.74
    Activations Density 0.032%

    No Known Activations