© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 168824
    Prev
    Next
    INDEX
    Explanations

    napper

    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
    çek
    0.47
    î
    0.46
     Grec
    0.43
    the
    0.42
    ês
    0.41
    ã
    0.41
     Norway
    0.41
     north
    0.40
     Antarctica
    0.40
     Long
    0.40
    POSITIVE LOGITS
     आईपी
    0.45
     спеціа
    0.43
     등의
    0.42
     جائے
    0.42
     operat
    0.42
     그리고
    0.42
    新的
    0.41
     efficaces
    0.41
     మరియు
    0.40
    篩
    0.40
    Activations Density 0.005%

    No Known Activations