© 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. 4002
    Prev
    Next
    INDEX
    Explanations

    what is expected

    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
    ong
    1.17
    েইলি
    1.02
    Ν
    0.92
     alleges
    0.91
     jeans
    0.89
    DEFGHIJKLMNOP
    0.89
    zám
    0.88
     absorbs
    0.88
     enclose
    0.86
    倆
    0.86
    POSITIVE LOGITS
    ا
    1.36
    ate
    1.17
    ق
    1.05
    𝗮
    1.02
    お
    1.00
    おり
    1.00
    ان
    0.98
    ్
    0.98
    น
    0.96
    Nicht
    0.95
    Activations Density 0.208%

    No Known Activations