© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 36959
    Prev
    Next
    INDEX
    Explanations

    language punctuation and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    $\
    0.42
    Seoul
    0.38
     harnessed
    0.38
    LTH
    0.37
    Panning
    0.37
    }%
    0.37
    }!
    0.36
     championship
    0.36
    }:
    0.36
     showcased
    0.36
    POSITIVE LOGITS
    逺
    0.45
     potrebbe
    0.43
    前面的
    0.41
     deben
    0.39
     शीघ्र
    0.39
     escrib
    0.39
    demir
    0.39
     senc
    0.38
     может
    0.38
     iniciando
    0.38
    Activations Density 0.024%

    No Known Activations