© 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. 110397
    Prev
    Next
    INDEX
    Explanations

    numbers, punctuation, and specific words

    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
     merupakan
    0.42
     sofern
    0.42
     Gründen
    0.41
     एड
    0.41
    а
    0.41
    ပါ။
    0.40
    .
    0.40
     harms
    0.40
    nels
    0.39
    fonts
    0.39
    POSITIVE LOGITS
     satiety
    0.47
     SCI
    0.47
     hypersurface
    0.45
    ఋ
    0.44
     transgenic
    0.44
    dip
    0.43
     asimismo
    0.42
     manifestaciones
    0.41
     Jpn
    0.41
     desorption
    0.41
    Activations Density 0.005%

    No Known Activations