© 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. 104818
    Prev
    Next
    INDEX
    Explanations

    foreign language text

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

    foreign or unusual characters

    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
     STEELS
    0.47
    ាល
    0.42
     Smoke
    0.42
     intelig
    0.42
     `<=
    0.41
    Debugging
    0.40
     heave
    0.40
     Concise
    0.40
     TREND
    0.40
    ल्स
    0.40
    POSITIVE LOGITS
    فیر
    0.51
    ayla
    0.46
     کھی
    0.46
     którym
    0.44
    utama
    0.41
    桀
    0.41
     نیز
    0.41
    elink
    0.41
     حوالہ
    0.41
    滈
    0.40
    Activations Density 0.000%

    No Known Activations