© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 27384
    Prev
    Next
    INDEX
    Explanations

    separation punctuation

    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
     Skins
    0.35
     über
    0.34
     it
    0.33
     over
    0.33
     something
    0.32
    ↵
    0.32
     the
    0.32
     growing
    0.32
    ↵↵↵
    0.31
     into
    0.31
    POSITIVE LOGITS
    ；
    0.39
    ;
    0.38
     sentenza
    0.38
    ፤
    0.37
    sequent
    0.37
     stoichi
    0.35
    ;|
    0.35
    ؛
    0.35
    acchus
    0.34
    vrd
    0.34
    Activations Density 0.072%

    No Known Activations