© 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. 126807
    Prev
    Next
    INDEX
    Explanations

    Latin America

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

    pinpoint the

    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
     dominance
    0.49
     myeloid
    0.45
     Transformation
    0.45
     причина
    0.44
     Causes
    0.43
    造成
    0.43
     Judaism
    0.43
    猙
    0.42
     uncompromising
    0.42
    쭉
    0.42
    POSITIVE LOGITS
    s
    0.59
    module
    0.53
    กรม
    0.48
    جہاں
    0.48
    鍑
    0.47
    fetchall
    0.47
    archiviato
    0.47
    panel
    0.46
    return
    0.46
    ref
    0.45
    Activations Density 0.000%

    No Known Activations