© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 15091
    Prev
    Next
    INDEX
    Explanations

    end of code statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    مل
    1.76
    ︹
    1.53
    cluster
    1.47
    ar
    1.40
    ╔
    1.38
    똑
    1.37
    Se
    1.35
     apps
    1.35
    ı
    1.32
     scratches
    1.31
    POSITIVE LOGITS
     materialize
    1.71
    ের
    1.67
    sighted
    1.63
    ഷ്യ
    1.54
     recebe
    1.51
    ್ಧ
    1.50
     fflush
    1.50
    PointXYZ
    1.49
    COUVER
    1.48
    s
    1.45
    Activations Density 0.141%

    No Known Activations