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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2063
    Prev
    Next
    INDEX
    Explanations

    javascript declarations and async

    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
    лянчук
    0.49
     次元
    0.48
    基因
    0.47
     galactose
    0.46
     peintre
    0.46
    壌
    0.46
     sondern
    0.46
    遺伝
    0.46
    <unused338>
    0.46
     рэгістрацыі
    0.45
    POSITIVE LOGITS
    let
    0.79
    if
    0.78
    const
    0.70
    var
    0.68
    ati
    0.67
    function
    0.64
    iti
    0.63
    aj
    0.62
    f
    0.62
    it
    0.61
    Activations Density 0.081%

    No Known Activations