© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 35204
    Prev
    Next
    INDEX
    Explanations

    isolation, empty, inclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     inú
    1.41
    ROTTLE
    1.33
    UCLEAR
    1.31
    перь
    1.30
    ನಗೆ
    1.30
    ૮
    1.28
     तौर
    1.27
     গ্রস্থ
    1.27
     forego
    1.27
    HOUT
    1.26
    POSITIVE LOGITS
    ین
    2.45
    ان
    2.08
    न
    1.99
    ant
    1.98
     a
    1.96
    li
    1.95
    ta
    1.95
    la
    1.92
    ת
    1.91
    st
    1.84
    Activations Density 0.001%

    No Known Activations