© 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. 36745
    Prev
    Next
    INDEX
    Explanations

    statement piece

    np_acts-logits-general · gemini-2.5-flash-lite

    installation, component, association

    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
    ÷
    0.46
    eth
    0.43
     ÷
    0.43
     berkaitan
    0.41
     使っ
    0.40
    ols
    0.39
    comes
    0.39
     Demonstr
    0.39
    ©
    0.38
     Reserved
    0.38
    POSITIVE LOGITS
    يد
    0.54
     uniqueness
    0.46
    assignmentItems
    0.45
    idyl
    0.44
    issão
    0.43
    тельном
    0.43
    ция
    0.43
    মেন্ট
    0.43
    室内
    0.43
    нном
    0.42
    Activations Density 0.000%

    No Known Activations