© 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. 111001
    Prev
    Next
    INDEX
    Explanations

    requested an

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

    authenticity, testing, or time

    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
    ，
    0.53
    es
    0.46
    ’
    0.44
    ASTM
    0.43
    AIN
    0.42
    1
    0.42
    挪
    0.41
    )
    0.40
     nay
    0.40
    mn
    0.39
    POSITIVE LOGITS
     kitabı
    0.55
     Tattha
    0.53
    ॓
    0.53
    زی
    0.48
     şey
    0.48
     ත
    0.47
     terrifying
    0.47
     która
    0.47
     Wahrheit
    0.46
     inquisitive
    0.45
    Activations Density 0.003%

    No Known Activations