© 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. 50692
    Prev
    Next
    INDEX
    Explanations

    seeing you

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

    changes and their consequences

    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
     prohibitions
    0.51
     売
    0.46
     pemasaran
    0.45
    ੳ
    0.45
     approvals
    0.44
    ཥ
    0.44
     społ
    0.44
     图片
    0.43
     '('
    0.42
     মুখপাত্র
    0.42
    POSITIVE LOGITS
    extend
    0.40
    olysis
    0.40
    quiet
    0.40
    **
    0.39
     witnessed
    0.39
    ę
    0.38
     காணப்படும்
    0.38
     фонда
    0.38
    ey
    0.38
    зацию
    0.37
    Activations Density 0.002%

    No Known Activations