© 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. 108043
    Prev
    Next
    INDEX
    Explanations

    account closure

    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
     čl
    0.40
     مط
    0.40
     configuring
    0.40
    नोमियल
    0.39
     simak
    0.39
    𝔀
    0.39
     സഹായി
    0.38
     projektu
    0.38
    譴
    0.38
     کمک
    0.37
    POSITIVE LOGITS
    in
    0.47
    er
    0.46
     Himalaya
    0.42
    流通
    0.41
    el
    0.41
    存在
    0.41
     Welt
    0.40
    䏹
    0.39
    ler
    0.39
     всех
    0.39
    Activations Density 0.006%

    No Known Activations