© 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. 81722
    Prev
    Next
    INDEX
    Explanations

    reduction, rights, value, best

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

    joy, soul, pilots, little

    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
     cib
    0.47
    ToWrite
    0.44
     díky
    0.43
    io
    0.43
     hin
    0.42
     myös
    0.42
    Implicit
    0.42
    Credential
    0.42
     ($\
    0.41
     includ
    0.41
    POSITIVE LOGITS
     Insulation
    0.43
     insulted
    0.42
    istem
    0.42
     Ultrasonic
    0.41
     compromises
    0.39
     Phosphate
    0.39
     डिस्ट्र
    0.39
     Smartphones
    0.38
    ಿಸಿಕೊಂಡ
    0.38
     상승
    0.38
    Activations Density 0.000%

    No Known Activations