© 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. 113348
    Prev
    Next
    INDEX
    Explanations

    parts, data, Penis

    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
    л
    0.55
     intracranial
    0.49
     irreducible
    0.48
    м
    0.48
    이
    0.46
    স
    0.46
     kilometers
    0.45
     infinity
    0.44
     mechanisms
    0.43
     expenditures
    0.43
    POSITIVE LOGITS
    rie
    0.43
    تباه
    0.41
    rit
    0.40
     时
    0.39
    dyna
    0.39
    تمع
    0.38
     adaptés
    0.38
    यान
    0.38
    Jamie
    0.38
     казіно
    0.38
    Activations Density 0.007%

    No Known Activations