© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 10845
    Prev
    Next
    INDEX
    Explanations

    white men or each color

    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_9_width_262k_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
    𝑈
    1.63
    teil
    1.41
    ᅴ
    1.38
    ្សែ
    1.32
    ٥
    1.30
    ٤
    1.28
     Caen
    1.24
    𝑅
    1.23
    ٦
    1.22
     linestyle
    1.21
    POSITIVE LOGITS
     unclear
    1.30
    说
    1.28
    Complete
    1.25
    e
    1.23
    י
    1.17
     complete
    1.16
     buộc
    1.15
     তত্ত্বাব
    1.15
    ും
    1.14
    但在
    1.14
    Activations Density 0.000%

    No Known Activations