© 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. 109773
    Prev
    Next
    INDEX
    Explanations

    the number seven

    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
    ا
    1.10
    in
    1.02
     сохра
    0.97
    shal
    0.93
    sw
    0.91
    ni
    0.91
    ch
    0.91
    ren
    0.91
    َ
    0.91
    zens
    0.89
    POSITIVE LOGITS
    ای
    1.10
    ि
    0.96
    ಿಯನ್
    0.89
    ü
    0.88
    ore
    0.86
    ви
    0.86
    들이
    0.85
    ת
    0.82
    üle
    0.81
    <0x80>
    0.80
    Activations Density 0.030%

    No Known Activations