© 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. 31-GEMMASCOPE-2-RES-262K
    7. 56803
    Prev
    Next
    INDEX
    Explanations

    understanding and asking questions

    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_31_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
     Hill
    0.45
     includes
    0.44
     mua
    0.43
     lists
    0.42
     HILL
    0.42
     B
    0.42
     White
    0.41
     adopts
    0.40
     Gold
    0.39
     scholarship
    0.39
    POSITIVE LOGITS
    焲
    0.52
     fácilmente
    0.48
    ૩
    0.48
    长时间
    0.47
    亽
    0.46
    复杂
    0.46
    Technische
    0.46
    다
    0.46
    ﺍ
    0.46
    esperienza
    0.45
    Activations Density 0.001%

    No Known Activations