© 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. 165756
    Prev
    Next
    INDEX
    Explanations

    . lot more

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

    ensures, crucial, takes, fuller

    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
    ル
    0.51
    筆
    0.50
     ನಾವು
    0.49
    れば
    0.49
    רו
    0.48
    ἱ
    0.47
     Все
    0.47
    ながら
    0.46
    ל
    0.46
     शुरुआत
    0.46
    POSITIVE LOGITS
     kæ
    0.48
     coercion
    0.46
     mojo
    0.45
     animal
    0.44
     inaccurate
    0.44
     indelible
    0.44
     arcane
    0.44
     flops
    0.43
     ciała
    0.43
     kanya
    0.43
    Activations Density 0.002%

    No Known Activations