© 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. 29-GEMMASCOPE-2-RES-65K
    7. 2365
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    銠
    0.92
     lLoginID
    0.88
    ㉖
    0.86
    Ᏻ
    0.83
    ᓐ
    0.83
     côtes
    0.82
    <unused8>
    0.81
    ᖅ
    0.80
     KRS
    0.80
    鉞
    0.78
    POSITIVE LOGITS
    <unused61>
    1.68
     t
    1.67
     hea
    1.50
    <unused62>
    1.50
     s
    1.47
     whi
    1.45
     н
    1.42
     wi
    1.38
    ｒ
    1.38
     р
    1.36
    Activations Density 1.522%

    No Known Activations