© 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. 182995
    Prev
    Next
    INDEX
    Explanations

    judging or saying

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

    building brand voice and tone

    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
    Negative Logits
    颞
    0.53
    קת
    0.50
    c
    0.50
    ת
    0.48
    볶
    0.48
    LAND
    0.48
    R
    0.48
    ُر
    0.47
    ଡ
    0.47
    AUTO
    0.46
    POSITIVE LOGITS
     judge
    0.49
     potter
    0.47
    iels
    0.47
     shooter
    0.46
     Halls
    0.46
     म्हणतात
    0.45
     Тар
    0.45
     presidency
    0.44
     Tidal
    0.44
     khal
    0.44
    Activations Density 0.000%

    No Known Activations