Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 49033
    Prev
    Next
    INDEX
    Explanations

    code assignment and comparison

    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
     exudes
    0.42
    ности
    0.39
    ทุกคน
    0.39
    জনে
    0.39
    年
    0.38
     существует
    0.38
    、
    0.37
     existe
    0.37
    ndon
    0.37
     savvy
    0.37
    POSITIVE LOGITS
    =='
    0.41
     Compressor
    0.40
    ే
    0.39
     specifico
    0.39
     Cál
    0.38
    ]=='
    0.37
    Bezier
    0.37
    ენტი
    0.37
    Univ
    0.37
    arynge
    0.37
    Activations Density 0.072%

    No Known Activations