© 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. 217669
    Prev
    Next
    INDEX
    Explanations

    qualification or standard

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

    conjunctions and explanations

    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
    त
    0.53
    ک
    0.51
    カメラ
    0.48
    廡
    0.47
     Tania
    0.46
     Fot
    0.45
    არა
    0.44
     এছ
    0.44
    ᠴ
    0.44
     enk
    0.44
    POSITIVE LOGITS
    markets
    0.50
    ücklich
    0.49
     社会
    0.49
    য়ন
    0.46
    INDEX
    0.46
    bid
    0.45
     বৈ
    0.45
    जीवी
    0.44
     最大
    0.44
     గౌ
    0.43
    Activations Density 0.000%

    No Known Activations