© 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. 86342
    Prev
    Next
    INDEX
    Explanations

    offers, gifts, and pinterest

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

    parts of speech, definitions, or descriptions

    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
    Metaxy
    0.49
    Meine
    0.48
    ንዱ
    0.46
    ギラ
    0.45
    G
    0.45
    ო
    0.44
    ichtig
    0.44
    棭
    0.44
     അനു
    0.43
    Hemos
    0.43
    POSITIVE LOGITS
     BREAK
    0.49
     restructure
    0.48
     Brux
    0.43
     BRA
    0.42
     Cumbria
    0.42
     plugs
    0.42
     Eat
    0.41
     Junction
    0.41
     Sav
    0.41
     BIN
    0.40
    Activations Density 0.007%

    No Known Activations