© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 108987
    Prev
    Next
    INDEX
    Explanations

    Titles, planners, stats

    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
    ↵↵
    0.44
     Sloane
    0.43
     halv
    0.43
    stdlib
    0.42
    null
    0.42
    largest
    0.42
    placeholder
    0.41
    speeds
    0.41
    r
    0.41
    progressive
    0.41
    POSITIVE LOGITS
     punctato
    0.60
     μουσ
    0.59
    owego
    0.57
     έχουν
    0.56
     говорят
    0.55
    鋲
    0.54
    𝟮
    0.54
     accusing
    0.52
     animación
    0.52
    𝗘
    0.52
    Activations Density 0.000%

    No Known Activations