© 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. 38883
    Prev
    Next
    INDEX
    Explanations

    names of things described or listed

    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
     பெயர்
    0.49
    fonction
    0.47
    kowego
    0.46
     عم
    0.44
     المث
    0.44
     Ə
    0.44
    cura
    0.43
     כת
    0.43
    cum
    0.43
    nombre
    0.43
    POSITIVE LOGITS
     ocasiones
    0.42
    ாக
    0.40
    اديم
    0.40
    рий
    0.40
    に
    0.40
    ளிடையே
    0.39
     murderous
    0.39
    er
    0.38
    رى
    0.38
     invasive
    0.38
    Activations Density 0.001%

    No Known Activations