© 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-16K
    7. 13047
    Prev
    Next
    INDEX
    Explanations

    watch some more videos

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

    deez nuts

    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_16k_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
    समझ
    0.49
     ಹಣ
    0.47
    হো
    0.46
    ಕೊ
    0.46
    㕕
    0.45
    uk
    0.44
    خی
    0.44
    ark
    0.44
    bases
    0.44
    städ
    0.44
    POSITIVE LOGITS
    ↵
    0.46
     defaultValue
    0.43
    ెక్
    0.43
     accolades
    0.40
    而言
    0.39
     igualmente
    0.39
     máxima
    0.39
     altid
    0.39
     beverage
    0.38
     doanh
    0.38
    Activations Density 0.019%

    No Known Activations