© 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. 12702
    Prev
    Next
    INDEX
    Explanations

    jace or hashtags

    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
    その
    1.21
     또는
    1.17
     sejumlah
    1.07
    または
    1.06
    与其
    1.06
    ுள்ளனர்
    1.03
     penggunaan
    1.02
    或
    1.02
     වශයෙන්
    1.02
     அல்லது
    1.00
    POSITIVE LOGITS
    1
    1.90
    2
    1.71
    8
    1.63
    0
    1.57
    6
    1.57
    7
    1.56
    9
    1.55
    4
    1.49
    5
    1.44
    3
    1.43
    Activations Density 0.087%

    No Known Activations