© 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. 33857
    Prev
    Next
    INDEX
    Explanations

    or

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

    seasonal or threat

    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
     উপাদান
    0.47
    রাল
    0.45
    _);
    0.44
    ﹉
    0.43
     নীতিমালা
    0.42
    honia
    0.42
     hilft
    0.41
    ✚
    0.41
     більше
    0.40
     উর্
    0.40
    POSITIVE LOGITS
     Esports
    0.55
     または
    0.52
     अर्थात्
    0.50
     ಯು
    0.49
    または
    0.47
     そして
    0.47
     ወይም
    0.46
     अथवा
    0.46
     oppure
    0.46
     அல்லது
    0.44
    Activations Density 0.000%

    No Known Activations