© 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. 28080
    Prev
    Next
    INDEX
    Explanations

    if clauses

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

    ordering, objective, general, standard

    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
     базу
    0.51
     pendapat
    0.49
     अहंकार
    0.47
     महत्त्व
    0.43
    ⿶
    0.43
     ரூ
    0.42
     सुकून
    0.42
     удоволь
    0.42
     машину
    0.42
     COMPARE
    0.42
    POSITIVE LOGITS
    从事
    0.46
    ier
    0.44
    itet
    0.43
    ocio
    0.42
    Le
    0.40
    freq
    0.39
    びに
    0.39
    ips
    0.39
    /
    0.39
    elt
    0.38
    Activations Density 0.000%

    No Known Activations