© 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. 168281
    Prev
    Next
    INDEX
    Explanations

    locations and time periods

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

    conservation of forms

    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
     রাহুল
    0.54
     イヤ
    0.48
     канализа
    0.48
    нта
    0.47
    স্বর
    0.47
     Проци
    0.46
     ビタミン
    0.45
    𒄷
    0.45
     カジュアル
    0.45
     肩
    0.45
    POSITIVE LOGITS
     plastik
    0.44
     leit
    0.42
     fet
    0.41
    दर्शी
    0.40
     Eng
    0.40
    ipedia
    0.40
     kest
    0.39
     här
    0.39
    Rig
    0.39
     ek
    0.38
    Activations Density 0.001%

    No Known Activations