© 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. 227415
    Prev
    Next
    INDEX
    Explanations

    description of state or quality

    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
     है
    0.52
    और
    0.52
     आहे
    0.47
    년에
    0.46
    है
    0.45
    ३
    0.45
     ਹੈ
    0.44
    三年
    0.44
     கண்டுபி
    0.43
    इसलिए
    0.43
    POSITIVE LOGITS
     amusement
    0.49
     amateur
    0.47
     ador
    0.46
     flickering
    0.44
     cipher
    0.44
     automata
    0.42
     ami
    0.39
     uninterrupted
    0.39
     selfies
    0.39
     Esports
    0.39
    Activations Density 0.002%

    No Known Activations