© 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. 51144
    Prev
    Next
    INDEX
    Explanations

    extent necessary

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

    technical terms, code, and management

    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
    a
    0.50
    റ്
    0.48
    haven
    0.48
    ok
    0.47
    ठीक
    0.46
    dropout
    0.46
    Looking
    0.46
    Scotland
    0.46
    Oke
    0.45
    execute
    0.45
    POSITIVE LOGITS
     খ
    0.47
     Algorithms
    0.47
     Antibodies
    0.47
     NEL
    0.47
     CHIKV
    0.46
     Raises
    0.46
     tableName
    0.46
     DIA
    0.46
     Antibody
    0.46
     LEN
    0.46
    Activations Density 0.002%

    No Known Activations