© 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. 16-GEMMASCOPE-2-RES-262K
    7. 48303
    Prev
    Next
    INDEX
    Explanations

    short & sweet

    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
     lect
    0.55
     incluye
    0.53
    }
    0.52
     stem
    0.48
     include
    0.47
     wholesome
    0.47
     transplantation
    0.47
     culpable
    0.46
     promoting
    0.46
     includes
    0.46
    POSITIVE LOGITS
    ™
    0.49
    ꒷
    0.48
    InitTypeDef
    0.47
    悆
    0.47
    ᗜ
    0.46
    Ꮺ
    0.46
    ₸
    0.46
    swiper
    0.46
    ಿದ್ದರೆ
    0.45
    ᓵ
    0.45
    Activations Density 0.000%

    No Known Activations