© 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. 37217
    Prev
    Next
    INDEX
    Explanations

    what is behind something

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

    behind the

    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
    ）；
    0.65
     гульнявыя
    0.63
     ентитету
    0.60
     другу
    0.59
     ৮ম
    0.59
    <unused1070>
    0.59
     திருதியை
    0.58
     as
    0.57
     топлива
    0.57
    の
    0.57
    POSITIVE LOGITS
     behind
    1.16
     Behind
    1.02
    Behind
    1.01
    behind
    0.96
     detrás
    0.90
    ก
    0.88
     dietro
    0.84
     derrière
    0.83
     atrás
    0.74
     (
    0.71
    Activations Density 0.019%

    No Known Activations