© 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. 28170
    Prev
    Next
    INDEX
    Explanations

    unusual or extreme situations

    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
     иногда
    0.45
     भावनात्मक
    0.44
     ofta
    0.43
     emocional
    0.43
     emotions
    0.42
     często
    0.42
    秅
    0.42
     भावनाओं
    0.41
    我可以
    0.41
     अक्सर
    0.41
    POSITIVE LOGITS
     reconsider
    0.45
     aston
    0.44
     shame
    0.43
     misunder
    0.43
    hene
    0.42
    rare
    0.40
    “
    0.40
     unheard
    0.40
     amaze
    0.39
     unthinkable
    0.38
    Activations Density 0.125%

    No Known Activations