© 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. 121463
    Prev
    Next
    INDEX
    Explanations

    sequences of action verbs

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

    analyze and document

    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
     മുതൽ
    0.44
    (%
    0.42
    人民政府
    0.42
     ㅎ
    0.41
    %%%%%%%%%%%%%%%%
    0.40
     சதவீ
    0.40
    могою
    0.40
     ৯০
    0.40
     மாதம்
    0.40
     получение
    0.40
    POSITIVE LOGITS
     and
    0.51
    and
    0.43
     programme
    0.38
    m
    0.38
     broadly
    0.38
    ont
    0.37
     games
    0.37
    ands
    0.36
     indeed
    0.36
     networks
    0.36
    Activations Density 0.023%

    No Known Activations