© 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. 114691
    Prev
    Next
    INDEX
    Explanations

    group insurance, collective efficacy, FastCGI

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

    functions, algorithms, and technical details

    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
    _
    0.57
    ﭥ
    0.53
     anos
    0.50
     humaines
    0.49
     mesmos
    0.48
     Nus
    0.48
     Ita
    0.47
     pars
    0.46
     antagonist
    0.46
    _;
    0.46
    POSITIVE LOGITS
     وقت
    0.55
     muối
    0.50
     गिरावट
    0.49
    時間を
    0.48
    сус
    0.46
     حجم
    0.46
     thuốc
    0.46
    選び
    0.45
     ईंधन
    0.45
     বায়ু
    0.44
    Activations Density 0.000%

    No Known Activations