© 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. 47610
    Prev
    Next
    INDEX
    Explanations

    Apple Music, Ghana Cedis, Leo Awards

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

    could legally, expanding, sounds

    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
    就开始
    0.50
    能力
    0.48
    谨慎
    0.46
    ционной
    0.45
     പരിശീല
    0.45
     இருந்தது
    0.44
    ことが多い
    0.43
    ي
    0.43
     முதலில்
    0.43
     inti
    0.43
    POSITIVE LOGITS
     labourers
    0.48
     taxes
    0.46
    \%,
    0.46
    ="))
    0.46
     refus
    0.45
     ইত্যা
    0.43
    ূন
    0.43
     "]";
    0.42
    に入れる
    0.42
    ಾದರೆ
    0.42
    Activations Density 0.000%

    No Known Activations