© 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. 37065
    Prev
    Next
    INDEX
    Explanations

    every population size

    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
    力和
    0.43
    ท
    0.42
     ق
    0.41
     முயற்
    0.40
    icoter
    0.40
    性和
    0.40
    ัศ
    0.40
    ア
    0.39
     الف
    0.39
    די
    0.39
    POSITIVE LOGITS
    也就是说
    0.49
    ensureEqual
    0.49
     correspondingly
    0.48
     ২০
    0.48
     Corresponding
    0.47
    的数据
    0.46
     surjective
    0.46
    LEFT
    0.45
    上限
    0.44
    },
    0.44
    Activations Density 0.003%

    No Known Activations