© 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. 40855
    Prev
    Next
    INDEX
    Explanations

    taking part

    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
    ן
    1.20
    us
    1.19
    ের
    1.16
    та
    1.16
    т
    1.16
    ти
    1.05
    ओं
    1.02
    у
    0.99
    тую
    0.93
    ی
    0.92
    POSITIVE LOGITS
    し
    1.11
    js
    0.90
    関
    0.87
    .
    0.85
    jší
    0.84
    C
    0.84
    お
    0.82
    ール
    0.81
    لك
    0.79
    見
    0.79
    Activations Density 0.000%

    No Known Activations