© 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. 63117
    Prev
    Next
    INDEX
    Explanations

    variable state

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

    harm, pregnancy, access, variable

    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
    衷
    0.50
    ö
    0.48
    ima
    0.47
    jär
    0.46
    bor
    0.45
    ler
    0.44
    ন্স
    0.44
    ובה
    0.44
    Bl
    0.44
    겐
    0.43
    POSITIVE LOGITS
     reutil
    0.58
     accounts
    0.52
     changeable
    0.51
     potenciales
    0.50
     variabile
    0.50
     reusable
    0.50
     variable
    0.49
     riesgo
    0.48
     tuy
    0.48
     creada
    0.48
    Activations Density 0.000%

    No Known Activations