© 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. 68999
    Prev
    Next
    INDEX
    Explanations

    songs, mod, railways, GPS

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

    algorithm, champion, load, pumping, Satoshi, end, run

    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
    ٥
    0.55
    和
    0.50
    ٤
    0.50
    ५
    0.49
    Deletion
    0.49
    üyor
    0.47
    ఏ
    0.46
    Transicao
    0.46
    ۵
    0.46
    എ
    0.45
    POSITIVE LOGITS
     spoonful
    0.46
     overheat
    0.45
    yanka
    0.45
    hank
    0.44
    stick
    0.42
     hydrant
    0.42
    khan
    0.42
     mouthful
    0.42
    getpath
    0.42
    ondere
    0.40
    Activations Density 0.000%

    No Known Activations