© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 39591
    Prev
    Next
    INDEX
    Explanations

    numbers and descriptions

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

    an evaluation or descriptor

    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
     центром
    0.47
     asignatura
    0.46
     étudier
    0.45
     centrales
    0.43
    स्टम
    0.42
    伽
    0.42
     अध्ययन
    0.42
     différences
    0.42
     অধ্যয়ন
    0.42
     zespo
    0.42
    POSITIVE LOGITS
     뭐가
    0.44
    くなる
    0.43
    osite
    0.41
    sp
    0.41
     html
    0.41
    ato
    0.41
     اطلع
    0.40
    unlink
    0.40
     Movie
    0.40
    sh
    0.39
    Activations Density 0.000%

    No Known Activations