© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 32853
    Prev
    Next
    INDEX
    Explanations

    descriptive and technical terms

    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
    a
    0.63
    an
    0.50
    en
    0.49
    빈
    0.49
    un
    0.46
    咕
    0.46
     eul
    0.45
    ர்ப
    0.44
    는
    0.43
    ip
    0.42
    POSITIVE LOGITS
     tertentu
    0.45
     trois
    0.44
     социальной
    0.44
     negatif
    0.43
    ovaný
    0.42
    
    0.42
     jiwa
    0.41
    和社会
    0.41
     восем
    0.41
    万里
    0.41
    Activations Density 0.002%

    No Known Activations