© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8509
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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_40_width_16k_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
     விஷய
    0.42
    acariy
    0.41
    это
    0.41
     любой
    0.39
     hacerlo
    0.38
    <unused1859>
    0.38
     restaurante
    0.38
    अच्छ
    0.37
     sự
    0.36
    <unused1162>
    0.35
    POSITIVE LOGITS
     (
    0.46
    ↵
    0.40
    ↵↵
    0.40
    /
    0.37
     colorful
    0.35
    )
    0.34
    }
    0.34
    。
    0.33
     ("
    0.33
    ।
    0.32
    Activations Density 0.067%

    No Known Activations