© 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. 78351
    Prev
    Next
    INDEX
    Explanations

    code comments and file paths

    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
     передний
    -0.82
     asado
    -0.82
    veien
    -0.82
    ✤
    -0.81
    imize
    -0.81
     Oran
    -0.81
    तर
    -0.80
    fiehlt
    -0.79
    imu
    -0.79
    Bem
    -0.79
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵
    1.01
     your
    1.00
    ↵↵↵↵↵↵
    0.99
    ↵↵↵↵↵↵↵↵↵
    0.99
     */
    0.98
    ↵↵↵
    0.98
    ↵↵↵↵
    0.95
     caminhos
    0.95
     like
    0.94
     pertenece
    0.93
    Activations Density 0.047%

    No Known Activations