© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 37758
    Prev
    Next
    INDEX
    Explanations

    adapters offer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     environnement
    0.47
    ను
    0.46
    िफ
    0.45
     на
    0.45
     környez
    0.44
     পরিবেশে
    0.44
    на
    0.44
     પ
    0.44
    。
    0.43
     পরিবেশ
    0.43
    POSITIVE LOGITS
    ppure
    0.50
    itant
    0.45
    comma
    0.43
    羣
    0.42
    __."
    0.42
     arba
    0.40
    indeed
    0.40
     uncommon
    0.39
    VOL
    0.39
    osoever
    0.39
    Activations Density 0.002%

    No Known Activations