© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 211282
    Prev
    Next
    INDEX
    Explanations

    Guterres said

    np_acts-logits-general · gemini-2.5-flash-lite

    history and technology concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recepción
    0.52
    翩
    0.48
     꽃
    0.46
    язви
    0.46
    寒
    0.46
    ertain
    0.46
    ecer
    0.45
    ingular
    0.42
    ریض
    0.42
    秋
    0.42
    POSITIVE LOGITS
     (
    0.49
     treated
    0.48
     ព
    0.47
     marginally
    0.46
    Subgraph
    0.46
    OrderID
    0.44
    OLE
    0.44
    ହା
    0.43
    ر
    0.43
     returned
    0.43
    Activations Density 0.000%

    No Known Activations