© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 7304
    Prev
    Next
    INDEX
    Explanations

    python and torch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_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
    s
    1.02
     quinto
    0.98
     fac
    0.94
     aparte
    0.94
    യാണ്
    0.93
     continuación
    0.90
    a
    0.90
     dann
    0.89
    puede
    0.88
     полови
    0.88
    POSITIVE LOGITS
    т
    1.52
    ramid
    1.09
    ruvate
    1.06
    서
    1.06
    啶
    1.04
    ні
    1.01
    thia
    1.00
    utrient
    0.99
    omena
    0.98
    า
    0.94
    Activations Density 0.099%

    No Known Activations