© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63833
    Prev
    Next
    INDEX
    Explanations

    unnecessary waste or overkill

    np_acts-logits-general · gemini-2.5-flash-lite

    unnecessary and redundant phrasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    臨時
    0.44
     entscheid
    0.44
     unforgettable
    0.40
     직접
    0.40
    袂
    0.40
     குற
    0.39
    🫦
    0.39
    मॉडल
    0.39
    탁
    0.39
     реши
    0.39
    POSITIVE LOGITS
     unnecessary
    1.90
     unnecessarily
    1.71
     needlessly
    1.67
     superfluous
    1.62
     अनावश्यक
    1.39
     inutile
    1.36
     inutil
    1.31
     useless
    1.28
     wasteful
    1.28
    浪费
    1.27
    Activations Density 0.142%

    No Known Activations