© 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. 47574
    Prev
    Next
    INDEX
    Explanations

    in a specific place

    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
     hanem
    -1.21
    которые
    -1.04
     société
    -1.00
     également
    -0.97
    とん
    -0.91
     lesquels
    -0.89
     caballo
    -0.85
    filterBy
    -0.85
     bonita
    -0.85
    おそ
    -0.85
    POSITIVE LOGITS
     now
    1.28
    īg
    0.99
     IBRARY
    0.90
     still
    0.88
    now
    0.87
     toată
    0.84
    quante
    0.83
    )');
    0.82
    ńcu
    0.82
     reach
    0.81
    Activations Density 0.049%

    No Known Activations