© 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-262K
    7. 23978
    Prev
    Next
    INDEX
    Explanations

    text formatting indicators

    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_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
    ة
    0.68
     a
    0.66
    ing
    0.48
     passa
    0.45
     leva
    0.45
    གས་
    0.44
     noi
    0.44
     kli
    0.44
     di
    0.43
     undergo
    0.43
    POSITIVE LOGITS
    Size
    0.57
    Existe
    0.55
    size
    0.54
    Só
    0.54
    C
    0.53
    ↵↵
    0.53
    Sizes
    0.53
    Це
    0.52
    QString
    0.51
    isPresent
    0.51
    Activations Density 0.011%

    No Known Activations