© 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. 10847
    Prev
    Next
    INDEX
    Explanations

    explanations and reasoning

    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
     describes
    0.37
    評價
    0.37
     depicts
    0.37
     뭐라고
    0.37
    舵
    0.37
    বাত
    0.37
    此
    0.36
    টাকে
    0.36
     根据
    0.35
     portrays
    0.35
    POSITIVE LOGITS
     или
    0.47
    obis
    0.42
     Loi
    0.41
    ิม
    0.39
     أو
    0.38
     ночью
    0.38
     (=
    0.37
     ຫຼື
    0.37
     அல்லது
    0.36
     һәм
    0.36
    Activations Density 0.342%

    No Known Activations