© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69682
    Prev
    Next
    INDEX
    Explanations

    if clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    These
    -2.08
     этих
    -1.79
     biß
    -1.73
     There
    -1.73
     pudiera
    -1.72
     aparentemente
    -1.70
     alterar
    -1.68
    }$.
    -1.66
     cathédrale
    -1.65
     destruir
    -1.64
    POSITIVE LOGITS
    ↵
    2.19
    such
    1.67
    </i>
    1.63
    筇
    1.51
     “
    1.49
      
    1.49
     ウエスト
    1.48
    IS
    1.43
    iciais
    1.39
     ales
    1.38
    Activations Density 0.001%

    No Known Activations