© 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. 11820
    Prev
    Next
    INDEX
    Explanations

    American presidents and diplomats

    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
     Mexique
    0.43
    형
    0.41
     ചെയ
    0.40
     مرح
    0.40
    墨西哥
    0.39
    ؎
    0.38
     Фор
    0.38
    വോ
    0.37
     haute
    0.37
    ሪ
    0.37
    POSITIVE LOGITS
     EF
    0.43
    scdn
    0.40
    Eres
    0.40
    iliter
    0.40
    apeti
    0.39
    ндә
    0.39
     Tetr
    0.39
     PCE
    0.39
     SCE
    0.39
     Rodgers
    0.38
    Activations Density 0.010%

    No Known Activations