© 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. 155570
    Prev
    Next
    INDEX
    Explanations

    days, hours, entrants, manuals

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

    tailored and designed for purpose

    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
     👀
    0.49
    Cab
    0.46
    During
    0.44
     🤔
    0.44
    Cabe
    0.44
    🙃
    0.42
     può
    0.42
    Throughout
    0.42
     durant
    0.41
     👋
    0.41
    POSITIVE LOGITS
     geeign
    0.53
     sử
    0.50
    以
    0.49
     کوشش
    0.46
     möglichst
    0.46
    合适的
    0.45
     используя
    0.45
     استفاده
    0.44
     utilizando
    0.44
     sesuai
    0.44
    Activations Density 0.002%

    No Known Activations