© 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. 52997
    Prev
    Next
    INDEX
    Explanations

    coryza and confidence

    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
     करतो
    0.49
    𝘪
    0.49
    erreur
    0.48
    된다
    0.48
    ท
    0.46
    实
    0.46
    aitement
    0.45
    Czas
    0.45
    ൦
    0.45
     Avoiding
    0.45
    POSITIVE LOGITS
     booths
    0.55
     boutique
    0.50
     afiliados
    0.49
     apparel
    0.48
     ancillary
    0.48
     tents
    0.46
     অন্য
    0.46
     hostels
    0.45
     outfits
    0.45
     swabs
    0.45
    Activations Density 0.004%

    No Known Activations