© 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. 161665
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

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

    specific examples

    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
    鈎
    0.51
    父母
    0.46
     altru
    0.45
    Yak
    0.45
    ពី
    0.45
     diarrhea
    0.45
    覺
    0.45
    煩
    0.45
    overlaps
    0.45
     diarr
    0.44
    POSITIVE LOGITS
     meriye
    0.50
    pyrazin
    0.45
    km
    0.43
     Ellsworth
    0.43
    ┣
    0.43
     ১২শ
    0.42
     Arte
    0.42
     impegn
    0.42
    ल्पनिक
    0.42
     Кри
    0.42
    Activations Density 0.000%

    No Known Activations