© 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. 246
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and technical data

    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
    Я
    0.53
    Α
    0.49
     deploying
    0.48
    부터
    0.48
    В
    0.47
    居
    0.47
    НА
    0.47
    М
    0.47
    “
    0.46
    ¿
    0.46
    POSITIVE LOGITS
    rj
    0.54
    ar
    0.54
    isn
    0.53
    inib
    0.53
    im
    0.52
    oc
    0.52
    ip
    0.52
    ac
    0.51
    inci
    0.51
    infodisc
    0.51
    Activations Density 0.000%

    No Known Activations