© 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. 103000
    Prev
    Next
    INDEX
    Explanations

    naked back, better decisions

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

    key features or specifications

    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
    xu
    0.42
    extrémité
    0.41
    海水
    0.41
    haut
    0.40
    Ｅ
    0.40
     defaul
    0.40
    釦
    0.39
    unitary
    0.39
    hout
    0.39
    鰓
    0.38
    POSITIVE LOGITS
    ycop
    0.50
     sedang
    0.47
    ছেন
    0.44
     рано
    0.44
     मॉड
    0.43
     stoked
    0.43
     svou
    0.43
     hablan
    0.42
    ́t
    0.42
     явно
    0.42
    Activations Density 0.000%

    No Known Activations