© 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. 184704
    Prev
    Next
    INDEX
    Explanations

    results section

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

    methods, results, description labels

    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
    ções
    0.49
     Effectiveness
    0.48
    避免
    0.46
    骛
    0.44
     problema
    0.43
    的问题
    0.43
    媒介
    0.43
     Manajemen
    0.42
    peut
    0.42
    :.
    0.41
    POSITIVE LOGITS
     ছবিটি
    0.46
     ಹೆಸ
    0.46
     నాలుగు
    0.43
     centroid
    0.43
     hava
    0.43
     oxidized
    0.42
     ingot
    0.42
     aluminium
    0.42
     loaned
    0.42
     nominally
    0.41
    Activations Density 0.001%

    No Known Activations