© 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. 28649
    Prev
    Next
    INDEX
    Explanations

    angled slightly

    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
    थाम
    0.46
    ujacy
    0.41
    ﾛ
    0.40
     herbivores
    0.39
    ﾏ
    0.39
    linge
    0.39
    ತಾ
    0.38
    ﾊ
    0.38
    Nombre
    0.38
    owaniu
    0.38
    POSITIVE LOGITS
     übrigens
    0.54
     separate
    0.45
     Separate
    0.44
     ligeramente
    0.40
     doesn
    0.40
     ayrıca
    0.40
     can
    0.39
     didn
    0.39
     unsur
    0.39
     همچنین
    0.38
    Activations Density 0.025%

    No Known Activations