© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11685
    Prev
    Next
    INDEX
    Explanations

    section introductions in lists

    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
     admire
    1.38
    🅔
    1.35
    dateTimePicker
    1.35
    ;\;\
    1.34
     austenite
    1.33
     surrounded
    1.32
     nestled
    1.30
     subjected
    1.29
     roam
    1.28
     معظم
    1.28
    POSITIVE LOGITS
    м
    1.51
    ви
    1.32
    이
    1.30
    in
    1.27
    imizin
    1.24
    ي
    1.22
    窓
    1.21
     mulighed
    1.17
    LR
    1.16
     aksi
    1.16
    Activations Density 0.046%

    No Known Activations