© 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. 11727
    Prev
    Next
    INDEX
    Explanations

    linking words and subsequent concepts

    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
    贄
    0.46
    दारों
    0.46
     protég
    0.44
     trif
    0.44
     perempt
    0.44
    killers
    0.43
    ން
    0.42
    ੰਜ
    0.42
     ToString
    0.42
    ިޔ
    0.42
    POSITIVE LOGITS
    ق
    0.55
    田
    0.52
    ad
    0.52
    手
    0.51
    ar
    0.50
    мо
    0.49
    aden
    0.48
    q
    0.48
    A
    0.46
    u
    0.46
    Activations Density 0.009%

    No Known Activations