© 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. 5705
    Prev
    Next
    INDEX
    Explanations

    are you or more information

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

    ultimately proven / unforeseen events

    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
    멀
    0.49
    гідно
    0.48
    ви
    0.45
    selfobj
    0.45
    ău
    0.44
    서
    0.44
    ड़ब
    0.44
    ৬০
    0.43
    рко
    0.43
    éfono
    0.43
    POSITIVE LOGITS
    0
    0.53
    ctions
    0.49
     知
    0.47
    ’
    0.47
    ifat
    0.46
     uitgen
    0.46
     อาท
    0.45
     ตอน
    0.45
     dakkh
    0.44
     เจ้า
    0.44
    Activations Density 0.000%

    No Known Activations