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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 101983
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

    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_all/layer_41_width_262k_l0_big
    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
    imageCache
    0.45
    ጋገብ
    0.44
    萵
    0.44
    ൯
    0.43
    ಲೆ
    0.42
    🍐
    0.41
     vulve
    0.41
    徫
    0.41
     endereco
    0.41
     seafront
    0.40
    POSITIVE LOGITS
    ̞
    0.85
    ͓
    0.83
    ̺
    0.83
    ͖
    0.82
    ͚
    0.81
    ̳
    0.80
    ̹
    0.79
    ͍
    0.78
    ̜
    0.78
    ̼
    0.77
    Activations Density 0.002%

    No Known Activations