© 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. 58105
    Prev
    Next
    INDEX
    Explanations

    variable stars

    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
    vnd
    -0.82
     propof
    -0.82
     spina
    -0.77
    Sola
    -0.75
     BASS
    -0.74
    ภูมิ
    -0.73
     gravi
    -0.71
     CORT
    -0.69
     Fenton
    -0.69
     comanda
    -0.69
    POSITIVE LOGITS
     puls
    0.98
     variable
    0.96
     Mira
    0.89
    Mira
    0.87
    VARIABLE
    0.85
     variability
    0.85
    变量
    0.85
     variables
    0.83
    dcterms
    0.79
    
    0.78
    Activations Density 0.042%

    No Known Activations