© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 40301
    Prev
    Next
    INDEX
    Explanations

    internal representation, efficiency, noise

    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
    дена
    0.49
    Annotations
    0.47
     कैलकु
    0.46
     широ
    0.45
    ưa
    0.43
    ;-
    0.43
    大き
    0.43
    делать
    0.42
     کہ
    0.42
    enarios
    0.42
    POSITIVE LOGITS
    astes
    0.48
    erian
    0.45
    town
    0.43
     offshore
    0.42
     resorts
    0.41
    蓍
    0.40
    鎭
    0.40
    acky
    0.39
    wrote
    0.39
     regionally
    0.39
    Activations Density 0.002%

    No Known Activations