© 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. 148178
    Prev
    Next
    INDEX
    Explanations

    'a' followed by a capitalized word

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

    put to sleep

    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
    ликт
    0.49
    Allison
    0.49
     здания
    0.48
    Claud
    0.45
    Mirror
    0.45
    Lily
    0.45
    Accent
    0.45
    ғ
    0.44
    ристи
    0.43
    faat
    0.43
    POSITIVE LOGITS
     apnea
    0.51
     ძალი
    0.51
     thơ
    0.49
     scom
    0.49
     edited
    0.48
     ジャ
    0.48
     insults
    0.47
     dė
    0.46
     θ
    0.46
    醫療
    0.46
    Activations Density 0.000%

    No Known Activations