© 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. 47817
    Prev
    Next
    INDEX
    Explanations

    call for submissions

    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
    trup
    -0.85
     грн
    -0.81
    Release
    -0.81
    mediaType
    -0.77
    هاد
    -0.77
    stornos
    -0.76
     básicas
    -0.73
    ogni
    -0.73
    的我
    -0.73
     Release
    -0.73
    POSITIVE LOGITS
     submit
    0.97
    SUBMIT
    0.91
    ubmit
    0.91
     submits
    0.89
     himself
    0.89
     SUBMIT
    0.87
     ura
    0.84
    Submit
    0.83
    ficulties
    0.82
     Kiz
    0.81
    Activations Density 0.008%

    No Known Activations