© 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. 1838
    Prev
    Next
    INDEX
    Explanations

    offering alternatives

    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
    altro
    0.54
    他の
    0.50
    ovaž
    0.49
    ಾ
    0.47
    ⺊
    0.47
    RES
    0.46
     berichtet
    0.46
     carattere
    0.45
    žu
    0.45
    㐌
    0.44
    POSITIVE LOGITS
     Hipp
    0.48
     High
    0.45
     Julie
    0.45
     Olivia
    0.44
     sessions
    0.44
     Identifying
    0.43
     subscription
    0.42
     sessionStorage
    0.42
     taxi
    0.41
     Hip
    0.41
    Activations Density 0.017%

    No Known Activations