© 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. 16-GEMMASCOPE-2-RES-262K
    7. 31727
    Prev
    Next
    INDEX
    Explanations

    beyond the scope

    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_16_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
    Ма
    0.59
    ಡ್
    0.57
     Ма
    0.55
     avantages
    0.54
    침
    0.54
     తగ్
    0.54
     انڈیا
    0.53
    프트
    0.52
    마
    0.52
    ೊಂಡು
    0.52
    POSITIVE LOGITS
    s
    0.61
    an
    0.60
    r
    0.59
     r
    0.51
    6
    0.49
     handling
    0.49
     handle
    0.48
     retali
    0.48
    alist
    0.47
     reread
    0.47
    Activations Density 0.045%

    No Known Activations