© 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. 68276
    Prev
    Next
    INDEX
    Explanations

    high sierra, syncup, oppression, problem, damage

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

    brand tone

    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
     europeos
    0.54
     européens
    0.51
     postérieures
    0.47
     lathes
    0.46
     européen
    0.46
     afternoons
    0.45
     semelhantes
    0.45
    穵
    0.45
    었고
    0.44
     americanos
    0.44
    POSITIVE LOGITS
    เหตุ
    0.40
    Infl
    0.40
     অ্যাল
    0.39
    intens
    0.38
     мере
    0.37
    在
    0.37
    $\
    0.36
    amp
    0.36
    volatile
    0.36
    (
    0.35
    Activations Density 0.000%

    No Known Activations