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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1225
    Prev
    Next
    INDEX
    Explanations

    parentheses and names

    np_acts-logits-general · gemini-2.5-flash-lite

    dictionary words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thiệt
    0.24
     autorités
    0.23
    骖
    0.23
     hidrat
    0.23
     expectativas
    0.23
     serão
    0.22
     tannin
    0.22
     thương
    0.22
    脤
    0.22
     benefici
    0.22
    POSITIVE LOGITS
    ld
    0.25
    all
    0.23
    apt
    0.21
    x
    0.21
    set
    0.21
    utf
    0.21
    item
    0.20
    name
    0.20
    ch
    0.20
    n
    0.20
    Activations Density 0.280%

    No Known Activations