© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24317
    Prev
    Next
    INDEX
    Explanations

    wordy, awkward, vague

    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
     surfaces
    0.40
     ensures
    0.40
     Mc
    0.38
     processes
    0.36
     d
    0.35
     depends
    0.35
     jug
    0.35
     sl
    0.35
     sounds
    0.35
     melibatkan
    0.34
    POSITIVE LOGITS
    亟
    0.63
     нужно
    0.56
     hindering
    0.56
    必须要
    0.55
    overty
    0.54
    лишком
    0.53
    阻
    0.52
     unnecessarily
    0.52
    需要
    0.51
     трябва
    0.49
    Activations Density 0.066%

    No Known Activations