© 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. 7930
    Prev
    Next
    INDEX
    Explanations

    most important component

    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
     prefque
    0.54
    濁
    0.50
     Summon
    0.50
     pâte
    0.50
    мун
    0.49
     bhave
    0.49
    墠
    0.49
    侃
    0.49
     ситуа
    0.48
     \%$,
    0.47
    POSITIVE LOGITS
     sua
    0.54
     vaccine
    0.51
     were
    0.49
     peptide
    0.48
     ribosome
    0.47
    '
    0.47
     circumference
    0.46
     ribosomal
    0.46
    0.46
     pathogen
    0.45
    Activations Density 0.011%

    No Known Activations