© 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. 76639
    Prev
    Next
    INDEX
    Explanations

    punctuation, lists, and non-English words

    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
    setPassword
    0.47
    ቃት
    0.46
    깝
    0.45
    வதும்
    0.40
    மொழ
    0.40
    kében
    0.40
    뀔
    0.40
     जीवों
    0.39
    োজ
    0.39
     potentials
    0.39
    POSITIVE LOGITS
    ی
    0.49
    。
    0.49
    "
    0.46
    чёт
    0.45
    '!
    0.44
     accruing
    0.44
    ”
    0.43
    ()
    0.41
     "/
    0.40
    cerr
    0.40
    Activations Density 0.007%

    No Known Activations