© 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. 57731
    Prev
    Next
    INDEX
    Explanations

    gardening plants or technical code inclusions

    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
     ecosistema
    -0.99
    $\$
    -0.98
     $\$
    -0.91
    Colored
    -0.90
    tized
    -0.89
     Mama
    -0.87
     provinciale
    -0.85
     Gurgaon
    -0.84
     centrale
    -0.84
    譎
    -0.83
    POSITIVE LOGITS
     autumn
    1.00
     HBV
    0.96
     sheltered
    0.92
    ׇ
    0.91
     shelter
    0.85
     RHS
    0.85
     galvan
    0.84
    庸
    0.84
     Kidney
    0.82
    RHS
    0.82
    Activations Density 0.026%

    No Known Activations