© 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. 191612
    Prev
    Next
    INDEX
    Explanations

    possessions and capabilities

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

    endless dance, imgsOut, Electro spinning

    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
    peration
    0.50
    '`--
    0.50
    ーストラリア
    0.49
    ୍କ
    0.46
     দূ
    0.46
    зам
    0.46
    েশন
    0.46
     kesulitan
    0.45
     proiz
    0.45
     플
    0.45
    POSITIVE LOGITS
     rendement
    0.49
     Increases
    0.46
    หนัง
    0.46
     banal
    0.45
    واره
    0.44
     jste
    0.44
     itemCount
    0.44
     rzecz
    0.44
    Increase
    0.43
    วาม
    0.43
    Activations Density 0.000%

    No Known Activations