© 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. 8556
    Prev
    Next
    INDEX
    Explanations

    workspaces and workshops

    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
    t
    1.54
    2
    0.95
    mu
    0.89
    től
    0.88
    𝐼
    0.84
    the
    0.83
    ۲
    0.83
    div
    0.80
    ée
    0.80
    見た
    0.80
    POSITIVE LOGITS
    те
    1.17
    ين
    1.16
    ни
    1.10
    ;
    0.93
    ය
    0.93
    મ
    0.91
    ності
    0.90
     HAS
    0.88
    ).}
    0.87
    )
    0.86
    Activations Density 0.024%

    No Known Activations