© 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. 131015
    Prev
    Next
    INDEX
    Explanations

    extreme tenacity

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

    Indian languages and geography

    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
    㶱
    0.48
    lai
    0.46
    
    0.45
    ROI
    0.44
    している
    0.43
    VIS
    0.43
     (=
    0.43
    ZG
    0.42
     tái
    0.42
    POSITIVE LOGITS
     fearless
    0.51
     tenacious
    0.44
     extreme
    0.44
     sonore
    0.43
     Rash
    0.42
     Extreme
    0.42
     tenacity
    0.42
     grueling
    0.42
     ekstrem
    0.41
     Glover
    0.41
    Activations Density 0.002%

    No Known Activations