© 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. 2108
    Prev
    Next
    INDEX
    Explanations

    URLs and filenames

    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
     \%
    0.27
     dessas
    0.26
     vasculature
    0.25
     damning
    0.25
     harmonies
    0.25
     zindagi
    0.25
     uphe
    0.24
     days
    0.24
     seeming
    0.24
     devastation
    0.24
    POSITIVE LOGITS
    ↵
    0.46
    .
    0.40
    us
    0.38
    i
    0.35
    '
    0.34
    u
    0.33
    ,
    0.33
    ut
    0.31
    d
    0.30
    is
    0.30
    Activations Density 0.159%

    No Known Activations