© 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. 44505
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts

    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
    saf
    0.49
    ambiental
    0.49
    Чтобы
    0.44
    ዟ
    0.44
    ad
    0.43
    d
    0.43
    rospective
    0.43
    rechte
    0.41
    v
    0.41
    dise
    0.41
    POSITIVE LOGITS
     وقت
    0.56
     जेब
    0.49
     beige
    0.49
     എല്ലാവ
    0.48
     thin
    0.45
     BE
    0.45
     HD
    0.45
     ವೇಳ
    0.45
     Dakar
    0.45
     час
    0.44
    Activations Density 0.000%

    No Known Activations