© 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-262K
    7. 38920
    Prev
    Next
    INDEX
    Explanations

    phrases indicating direction or focus

    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_262k_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
     Assumptions
    0.47
     via
    0.39
     acknowledge
    0.38
     provenant
    0.38
     atop
    0.38
     Derived
    0.38
    酮
    0.37
     +
    0.37
     ایسے
    0.37
    ند
    0.37
    POSITIVE LOGITS
    ütfen
    0.44
     упраж
    0.44
    ﹁
    0.43
    songwriter
    0.43
    Вели
    0.43
     plaît
    0.42
    Workout
    0.42
    蛐
    0.42
    Unit
    0.41
    BtnFill
    0.41
    Activations Density 0.004%

    No Known Activations