© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46484
    Prev
    Next
    INDEX
    Explanations

    speed and freedom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     documenti
    0.46
     разобраться
    0.45
     dokument
    0.44
     tersebut
    0.43
     ć
    0.43
     Wart
    0.43
     discutir
    0.42
     Game
    0.42
     documento
    0.42
     localizar
    0.41
    POSITIVE LOGITS
    ῶ
    0.43
    7
    0.42
    自動
    0.41
    陽
    0.41
     vielf
    0.40
    웹
    0.40
     עם
    0.39
    5
    0.38
    יר
    0.38
    ισμό
    0.38
    Activations Density 0.008%

    No Known Activations