© 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. 229111
    Prev
    Next
    INDEX
    Explanations

    parents/guardians, detoxing, antigens, London

    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
    <start_of_image>
    0.53
     كلمات
    0.48
     Philharmonic
    0.46
    Ả
    0.45
    ्र
    0.44
     licenciado
    0.43
     lembaga
    0.42
     concl
    0.42
    Ɵ
    0.42
     likewise
    0.42
    POSITIVE LOGITS
    normalization
    0.50
     Função
    0.49
     pathophysiology
    0.49
    事
    0.48
    ews
    0.48
    hbase
    0.47
    ored
    0.46
    uddersfield
    0.45
     peach
    0.45
     ପ୍ର
    0.45
    Activations Density 0.000%

    No Known Activations