© 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. 31-GEMMASCOPE-2-RES-262K
    7. 79957
    Prev
    Next
    INDEX
    Explanations

    classifying types of content

    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
    Through
    0.47
     through
    0.46
    sthrough
    0.46
    G
    0.46
    通过
    0.45
     Through
    0.44
     easy
    0.44
     melalui
    0.44
     dans
    0.43
     fácil
    0.43
    POSITIVE LOGITS
    ಡುವ
    0.52
    }((
    0.46
    recursive
    0.45
    appliquer
    0.44
    folding
    0.43
     Siam
    0.43
     تجي
    0.43
    㕵
    0.43
    degree
    0.42
    ndrome
    0.42
    Activations Density 0.001%

    No Known Activations