© 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-16K
    7. 12676
    Prev
    Next
    INDEX
    Explanations

    scanning objects or states

    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_16k_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
    ні
    2.55
    ная
    2.16
    т
    2.14
    ни
    2.08
    ת
    2.02
    сть
    2.00
    ம்
    1.91
    ח
    1.91
    ું
    1.89
    га
    1.85
    POSITIVE LOGITS
     وعلى
    1.84
     îl
    1.66
    the
    1.59
    j
    1.55
    CT
    1.54
    ud
    1.53
    w
    1.53
    wia
    1.52
    verlet
    1.52
     gesetzt
    1.49
    Activations Density 0.014%

    No Known Activations