© 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. 205146
    Prev
    Next
    INDEX
    Explanations

    before storing, charged as

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

    examples of diverse contexts

    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
    -
    0.46
     Field
    0.43
    ब
    0.42
    4
    0.42
    7
    0.40
    us
    0.40
    েম
    0.39
    }
    0.39
    <0x99>
    0.39
    場合
    0.39
    POSITIVE LOGITS
    nutrient
    0.52
     hommage
    0.51
     اكو
    0.50
    membre
    0.49
     supaya
    0.48
     makhluk
    0.47
    naissance
    0.47
     opulent
    0.47
     masukkan
    0.46
     ډاونلوډ
    0.46
    Activations Density 0.003%

    No Known Activations