© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 129408
    Prev
    Next
    INDEX
    Explanations

    contrast, comparison, clarification

    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
     लेकिन
    -1.69
     and
    -1.64
    ———-
    -1.63
    ——–
    -1.58
     gruppen
    -1.58
     cuci
    -1.55
     but
    -1.53
    }
    -1.52
    ()}
    -1.52
    —————
    -1.49
    POSITIVE LOGITS
     ...
    1.69
     were
    1.68
     这
    1.53
     kommenden
    1.42
    Não
    1.41
    Unis
    1.40
     i
    1.39
      
    1.39
     weren
    1.39
     I
    1.38
    Activations Density 0.012%

    No Known Activations