© 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. 164680
    Prev
    Next
    INDEX
    Explanations

    and new

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

    affirmative interjection or greeting

    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
    軒
    0.55
    製の
    0.50
    制造业
    0.49
    ウ
    0.49
     celulares
    0.47
    स्ट
    0.46
     umbrellas
    0.45
    栽
    0.45
    味噌
    0.45
    ಲ
    0.45
    POSITIVE LOGITS
    Mathematics
    0.50
    Description
    0.48
     detour
    0.46
     Mathematics
    0.44
     typescript
    0.44
     பரபர
    0.44
     besk
    0.43
     wildcard
    0.43
    forall
    0.43
     yy
    0.43
    Activations Density 0.001%

    No Known Activations