© 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. 124772
    Prev
    Next
    INDEX
    Explanations

    provided you, business automation, mice 6, record strait, reappear again

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

    restricted knowledge nuclear weapons

    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
    ро
    0.48
    ოგ
    0.47
    ក្រោម
    0.45
    キング
    0.45
     sobbing
    0.45
     lágrimas
    0.44
    긋
    0.44
    樵
    0.44
     versões
    0.44
    퇸
    0.44
    POSITIVE LOGITS
    ＼
    0.45
    ;
    0.43
    umers
    0.41
    :
    0.40
    inci
    0.39
    ducted
    0.39
     Loire
    0.39
    uba
    0.38
    olutions
    0.38
     省
    0.38
    Activations Density 0.001%

    No Known Activations