© 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. 40508
    Prev
    Next
    INDEX
    Explanations

    bullet points and lists

    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
    the
    0.44
    entire
    0.42
    basicConfig
    0.41
    www
    0.41
    nThe
    0.41
     very
    0.40
     ,
    0.39
     entire
    0.39
     predicted
    0.39
    getAll
    0.39
    POSITIVE LOGITS
     toekomst
    0.51
     осві
    0.47
     тях
    0.45
    راحة
    0.44
    ન્સ
    0.43
     ისინი
    0.43
     itp
    0.43
    רי
    0.42
     مزید
    0.42
    ᆷ
    0.42
    Activations Density 0.190%

    No Known Activations