© 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. 36002
    Prev
    Next
    INDEX
    Explanations

    beginning or before

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

    combining into a cohesive description

    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
    軖
    0.47
     различных
    0.46
    стки
    0.45
    insect
    0.44
    discussion
    0.42
     různých
    0.42
    traffic
    0.42
    ník
    0.42
     собак
    0.42
    inse
    0.41
    POSITIVE LOGITS
     बढ़ाकर
    0.49
     Gemeinschaft
    0.43
     exponential
    0.43
    ເລ
    0.43
     ///
    0.42
     Qu
    0.42
     Substance
    0.42
     Amherst
    0.42
     reimag
    0.41
     خم
    0.41
    Activations Density 0.000%

    No Known Activations