© 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. 54950
    Prev
    Next
    INDEX
    Explanations

    experienced, devoted, security

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

    combines, RSI, Guardians, Announcements

    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
     कंड
    0.48
    پے
    0.48
     посети
    0.47
     ២
    0.47
    prising
    0.46
     سبب
    0.46
     بدور
    0.45
     بد
    0.44
     страни
    0.43
     hars
    0.43
    POSITIVE LOGITS
    는
    0.52
     Prem
    0.51
     solves
    0.49
    Prem
    0.48
    的所有
    0.46
    .*/
    0.46
     Confucian
    0.45
    錦
    0.44
     Aqui
    0.43
     Drain
    0.43
    Activations Density 0.000%

    No Known Activations