© 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. 138482
    Prev
    Next
    INDEX
    Explanations

    shock wave

    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
    )،
    0.61
    وم
    0.60
    )、
    0.60
     ສຳ
    0.59
    マ
    0.59
    મ
    0.59
    ൻ
    0.57
    য়া
    0.56
    Cad
    0.55
    ctions
    0.54
    POSITIVE LOGITS
    s
    0.65
    druck
    0.57
    d
    0.56
     Schuh
    0.55
    as
    0.55
    ের
    0.55
    ื่อน
    0.55
    dır
    0.54
    ın
    0.53
    circa
    0.53
    Activations Density 0.000%

    No Known Activations