© 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. 62176
    Prev
    Next
    INDEX
    Explanations

    well known, cannot simply, easy way

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

    phrase length

    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
     círculo
    0.47
    煮
    0.46
    涂
    0.45
    جي
    0.44
    口感
    0.43
    ليزية
    0.43
    synt
    0.43
    細菌
    0.42
    鋭
    0.42
     pracuje
    0.41
    POSITIVE LOGITS
     or
    0.52
     или
    0.51
     kilowatt
    0.51
     エア
    0.48
     ihm
    0.48
     タイ
    0.47
     singles
    0.47
     rév
    0.47
     ማን
    0.46
     හෝ
    0.45
    Activations Density 0.000%

    No Known Activations