© 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. 64085
    Prev
    Next
    INDEX
    Explanations

    #include path/file names

    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
    PRIME
    -0.91
     Google
    -0.87
    Prime
    -0.85
     Prime
    -0.84
    Google
    -0.79
     lustrous
    -0.76
    olingo
    -0.74
     apprehensive
    -0.73
     Sonoma
    -0.73
     hectic
    -0.72
    POSITIVE LOGITS
     XJ
    0.90
     wim
    0.84
    𝒞
    0.83
     sequencing
    0.79
    atorias
    0.76
     Sequencing
    0.75
    stos
    0.74
    setCancelable
    0.73
     forKey
    0.72
    fwrite
    0.72
    Activations Density 0.032%

    No Known Activations