© 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. 70643
    Prev
    Next
    INDEX
    Explanations

    Kite Beach, anniversary!!

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

    refuse harmful content; compress abdomen

    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
    ApiClient
    0.49
    i
    0.49
     logins
    0.49
    agger
    0.46
     explaining
    0.46
     instabilities
    0.45
    fy
    0.45
    ra
    0.44
    你
    0.44
    ja
    0.44
    POSITIVE LOGITS
    십
    0.47
    িণ
    0.46
    <unused11>
    0.44
     животных
    0.44
    annon
    0.44
    뿡
    0.43
    ASCADE
    0.43
    먹
    0.43
    꼰
    0.42
     Rie
    0.42
    Activations Density 0.000%

    No Known Activations