© 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. 108604
    Prev
    Next
    INDEX
    Explanations

    dictionary, sequencing, or conceptual definitions

    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
    дий
    0.43
    ২৭
    0.42
    диа
    0.42
    !”,
    0.42
    °,
    0.41
     Communists
    0.40
     einzigen
    0.40
    ర్‌
    0.40
    秚
    0.40
    చ్
    0.39
    POSITIVE LOGITS
     Hollywood
    0.46
     faux
    0.44
    iejs
    0.43
    สิ่งที่
    0.42
     অত্যাচারের
    0.41
    おそらく
    0.41
     взаимо
    0.40
     muzy
    0.40
     seigneur
    0.40
     mogul
    0.39
    Activations Density 0.006%

    No Known Activations