© 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-65K
    7. 2845
    Prev
    Next
    INDEX
    Explanations

    specific word substrings

    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_65k_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
     школова
    0.42
    ადი
    0.40
    籠
    0.39
     accents
    0.39
    泊
    0.38
     orchids
    0.38
    وشی
    0.38
    azone
    0.37
     accent
    0.37
    ರ್ಮ
    0.36
    POSITIVE LOGITS
     Atr
    0.39
     Research
    0.39
     Anal
    0.38
     Log
    0.38
    іл
    0.37
    vs
    0.37
     An
    0.37
    厛
    0.37
    ❿
    0.36
    ें
    0.36
    Activations Density 0.001%

    No Known Activations