© 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. 113767
    Prev
    Next
    INDEX
    Explanations

    party bus outing

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

    As a [role]

    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
    는데
    0.53
    💏
    0.48
    Vacancy
    0.46
     sostit
    0.45
    ﻄ
    0.44
     ۔
    0.44
    𝓾
    0.43
    ાન
    0.43
    टू
    0.43
    ❤❤
    0.43
    POSITIVE LOGITS
     JN
    0.50
     Nguyễn
    0.49
     Bistro
    0.45
    }{
    0.45
     Jura
    0.45
     Brexit
    0.44
     DDT
    0.43
     DN
    0.43
     ONE
    0.42
     AK
    0.42
    Activations Density 0.001%

    No Known Activations