© 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. 148377
    Prev
    Next
    INDEX
    Explanations

    teams and events

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

    trying to find

    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
     donnent
    0.48
     epilepsy
    0.45
    нець
    0.45
    에요
    0.44
    শুধ
    0.43
    뗀
    0.43
     душу
    0.42
    วจ
    0.41
     insufficiently
    0.41
    nolds
    0.40
    POSITIVE LOGITS
    实时
    0.48
     টিম
    0.47
    ey
    0.47
    ادر
    0.46
    培
    0.46
    搏
    0.44
     spectra
    0.44
    标志
    0.43
     team
    0.43
     cAMP
    0.43
    Activations Density 0.001%

    No Known Activations