© 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. 66765
    Prev
    Next
    INDEX
    Explanations

    used equipment or specialized items

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

    conversation and follow-ups

    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
     nhưng
    0.51
     pero
    0.48
     কিন্তু
    0.45
    ?
    0.45
     BUT
    0.44
     Cantonese
    0.44
     nhiều
    0.43
     (=
    0.43
     tetapi
    0.43
     groupBox
    0.43
    POSITIVE LOGITS
    или
    0.55
    ឬ
    0.49
    婚姻
    0.49
    ኛውም
    0.48
     혹은
    0.46
    UNDS
    0.45
     오늘은
    0.45
    prestations
    0.45
    ג
    0.45
    適切
    0.45
    Activations Density 0.001%

    No Known Activations