© 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. 229386
    Prev
    Next
    INDEX
    Explanations

    obey my voice

    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
     erros
    0.56
    decrease
    0.54
    daily
    0.50
    direction
    0.49
    (|
    0.49
    vii
    0.48
     তৃণ
    0.47
    Errors
    0.46
    cult
    0.46
    catalog
    0.45
    POSITIVE LOGITS
    ن
    0.59
    前
    0.45
    مل
    0.45
     Vort
    0.44
    னை
    0.42
     ventilated
    0.42
    后再
    0.42
    后
    0.42
    च्छेद
    0.42
    巴
    0.42
    Activations Density 0.001%

    No Known Activations