© 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. 48680
    Prev
    Next
    INDEX
    Explanations

    protobuf imports in Go

    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
    çoivent
    0.51
    ؤ
    0.44
     apparence
    0.44
    忧
    0.43
     абсолютно
    0.42
     있어야
    0.42
    षभ
    0.42
    ilize
    0.42
    ጶ
    0.41
     ನನಗೆ
    0.41
    POSITIVE LOGITS
     polymerase
    0.54
     wellknown
    0.47
     seda
    0.46
    প্ট
    0.45
     plasmid
    0.44
     invertebrates
    0.44
     chub
    0.44
     drinks
    0.43
    http
    0.43
     tasty
    0.42
    Activations Density 0.006%

    No Known Activations