Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 41780
    Prev
    Next
    INDEX
    Explanations

    gray area

    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
     to
    1.18
    t
    0.90
    q
    0.88
    v
    0.85
    is
    0.83
    ge
    0.81
    其他
    0.81
    ت
    0.80
    en
    0.79
    ul
    0.79
    POSITIVE LOGITS
     validations
    0.66
     कोणताही
    0.63
     validated
    0.60
    urndata
    0.59
    2
    0.58
     страна
    0.57
    ަލ
    0.56
     clínico
    0.56
     contagion
    0.56
    SD
    0.55
    Activations Density 0.001%

    No Known Activations