© 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. 15146
    Prev
    Next
    INDEX
    Explanations

    describing situations or states

    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
     Textile
    0.53
    6
    0.50
    7
    0.49
    3
    0.48
     of
    0.47
    ях
    0.47
     Из
    0.47
    1
    0.46
    Tại
    0.46
     Build
    0.45
    POSITIVE LOGITS
    汜
    0.47
    beqz
    0.46
     stillness
    0.45
     vasena
    0.44
    $)$.
    0.44
     coolness
    0.44
     veineux
    0.43
     neder
    0.43
    នុស្ស
    0.43
     ฮะ
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.