© 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. 22451
    Prev
    Next
    INDEX
    Explanations

    describing correctness or quality

    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
     fabriqué
    0.44
     제조
    0.42
     ευρώ
    0.41
    棌
    0.40
     hergestellt
    0.39
     spécifique
    0.39
     제품
    0.38
     offrir
    0.38
    넬
    0.38
    檴
    0.38
    POSITIVE LOGITS
     neatly
    0.46
     complaining
    0.43
     wounds
    0.42
     wounded
    0.41
     women
    0.40
     housing
    0.38
     writing
    0.38
     suffering
    0.38
     slight
    0.38
     rebuilding
    0.37
    Activations Density 0.001%

    No Known Activations