© 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. 161837
    Prev
    Next
    INDEX
    Explanations

    . following words

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

    available, supply, or

    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
    %";
    0.51
    তম
    0.49
     »,
    0.48
    间的
    0.48
    Morning
    0.47
    าน
    0.46
    Supp
    0.46
    Theory
    0.46
    outro
    0.45
    culus
    0.45
    POSITIVE LOGITS
    走行
    0.47
     splendor
    0.45
     reple
    0.44
    쌈
    0.43
     willst
    0.42
     armament
    0.42
     moim
    0.42
     목적
    0.41
    쇤
    0.41
     easements
    0.41
    Activations Density 0.000%

    No Known Activations