© 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. 4157
    Prev
    Next
    INDEX
    Explanations

    categorical concepts

    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
     मित्त
    0.42
     Jetzt
    0.41
    راك
    0.39
    ewel
    0.39
    戽
    0.39
     Hoyt
    0.38
    ificial
    0.38
     Siempre
    0.37
    壘
    0.37
     Dieu
    0.37
    POSITIVE LOGITS
     assessed
    0.46
     was
    0.45
     autom
    0.45
     were
    0.44
     excreted
    0.44
     physiologically
    0.43
     categorical
    0.42
     평가
    0.42
     medicare
    0.42
     sanguin
    0.42
    Activations Density 0.025%

    No Known Activations