© 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. 129622
    Prev
    Next
    INDEX
    Explanations

    generation, business, children, process, Sea, parties

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

    text-based representations of data

    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
     أجل
    0.51
    ámica
    0.51
    '},
    0.50
    }'],
    0.49
    部长
    0.46
    WithOwner
    0.45
    ridor
    0.45
    运维
    0.45
    ポーチ
    0.45
    zej
    0.44
    POSITIVE LOGITS
     Fant
    0.52
     dawned
    0.48
     GRAY
    0.48
     Cric
    0.46
     Fairfax
    0.46
     Caught
    0.46
     TECHN
    0.45
    瑕
    0.44
     Favre
    0.44
     SK
    0.43
    Activations Density 0.000%

    No Known Activations