© 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. 107405
    Prev
    Next
    INDEX
    Explanations

    Allied Races, opportunity, emergency

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

    safety and danger

    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
     cudd
    0.57
     Anglican
    0.52
     by
    0.51
     bây
    0.51
     Viscount
    0.51
    </td>
    0.50
     b
    0.48
     भरकर
    0.48
     anhand
    0.47
     iff
    0.47
    POSITIVE LOGITS
    Однако
    0.51
    メン
    0.48
    卻
    0.48
    聯盟
    0.47
    Denn
    0.47
    Meu
    0.46
    却
    0.46
    僥
    0.46
    SCIENCE
    0.45
    ለያዩ
    0.45
    Activations Density 0.000%

    No Known Activations