© 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. 127835
    Prev
    Next
    INDEX
    Explanations

    detect grammatical errors

    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
     drinks
    0.48
     mains
    0.46
     vectorial
    0.44
    ע
    0.44
     tickers
    0.44
     ricord
    0.43
     buses
    0.43
     simil
    0.43
     trains
    0.42
     mili
    0.42
    POSITIVE LOGITS
     Gramm
    0.60
    extrait
    0.55
    ουν
    0.55
     Weights
    0.53
    грам
    0.52
     جلد
    0.52
     격
    0.50
    рам
    0.49
    weights
    0.49
    éléments
    0.48
    Activations Density 0.020%

    No Known Activations