© 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. 20599
    Prev
    Next
    INDEX
    Explanations

    performance calculations

    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
    antan
    0.46
    any
    0.46
    ho
    0.44
    ani
    0.43
    u
    0.43
     некоторы
    0.43
     неко
    0.42
    醫療
    0.42
    బో
    0.41
    ari
    0.40
    POSITIVE LOGITS
    气的
    0.47
    气体
    0.47
     hız
    0.46
     pręd
    0.43
     propulsion
    0.43
     speed
    0.42
    дм
    0.41
     дві
    0.41
    操控
    0.41
    ✌
    0.41
    Activations Density 0.015%

    No Known Activations