© 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. 50557
    Prev
    Next
    INDEX
    Explanations

    commands or advice

    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
    𝚕
    0.50
    लिसा
    0.49
     convain
    0.47
    šte
    0.47
     cít
    0.46
    ັບ
    0.44
    ittaa
    0.43
     niece
    0.42
     gyn
    0.42
     neue
    0.42
    POSITIVE LOGITS
    ரா
    0.45
    子の
    0.44
    Р
    0.41
     Iter
    0.41
    اسی
    0.41
    0
    0.41
     polish
    0.38
     Corpus
    0.38
    国の
    0.38
     Khan
    0.37
    Activations Density 0.000%

    No Known Activations