© 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. 1790
    Prev
    Next
    INDEX
    Explanations

    within text or code

    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
    )^*
    0.45
    ท
    0.45
    SAR
    0.44
    AG
    0.43
    장
    0.42
    HCM
    0.41
    TISE
    0.40
     APPEND
    0.40
    )->
    0.40
    ุน
    0.39
    POSITIVE LOGITS
     lehetős
    0.47
     máte
    0.45
    slidesPer
    0.43
    families
    0.42
     ثانوي
    0.42
    loadNpm
    0.42
     magnolia
    0.42
    padă
    0.41
    ដែល
    0.41
     ditth
    0.41
    Activations Density 0.007%

    No Known Activations