© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 248059
    Prev
    Next
    INDEX
    Explanations

    Copyright statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Course
    0.52
    Operand
    0.49
    ]++;
    0.48
     переменных
    0.48
    ọt
    0.47
    _{\{
    0.47
    onOptions
    0.46
    ikal
    0.45
    atik
    0.45
    okat
    0.45
    POSITIVE LOGITS
     conserv
    0.52
     ACE
    0.52
     conserve
    0.50
     Id
    0.49
    id
    0.48
     we
    0.48
     Conserv
    0.48
    <0x80>
    0.48
     BCH
    0.48
     Salmonella
    0.47
    Activations Density 0.001%

    No Known Activations