© 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. 101810
    Prev
    Next
    INDEX
    Explanations

    made to

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

    toxic families, mulch, context, optical, light drizzle

    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
    ・・・。
    0.52
     ...
    0.46
    PACT
    0.46
    PAD
    0.45
    ___
    0.44
    ელი
    0.44
     Tunis
    0.44
    designated
    0.44
    ុ
    0.44
    اول
    0.44
    POSITIVE LOGITS
    িয়৷
    0.49
     змен
    0.49
     умень
    0.48
     моделей
    0.47
     wayside
    0.45
     rougeâtre
    0.44
    ஆக
    0.43
     ऑग
    0.43
     quelquefois
    0.42
     eignet
    0.42
    Activations Density 0.002%

    No Known Activations