© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63095
    Prev
    Next
    INDEX
    Explanations

    color names, coding, questions

    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_34/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
    Etymology
    -0.82
     materna
    -0.78
    专注
    -0.74
    ≠
    -0.74
     secreto
    -0.74
     symbol
    -0.73
     Supremo
    -0.73
    WHERE
    -0.71
    except
    -0.70
    Except
    -0.69
    POSITIVE LOGITS
     green
    0.96
     zöld
    0.91
     Green
    0.87
     GREEN
    0.81
    lüğü
    0.80
     considération
    0.78
    Green
    0.77
     alpha
    0.76
     GetAll
    0.76
    眶
    0.75
    Activations Density 0.005%

    No Known Activations