© 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. 3629
    Prev
    Next
    INDEX
    Explanations

    itinerary or trajectory

    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
    al
    1.80
    ah
    1.68
     iż
    1.67
    ine
    1.66
    arono
    1.59
    をする
    1.58
    に対応
    1.58
    ख
    1.57
     दिला
    1.54
    ong
    1.53
    POSITIVE LOGITS
    tı
    2.20
    FORM
    2.14
    ารย์
    2.13
    ted
    2.09
    그램
    2.09
    ي
    2.03
    tip
    1.98
    sman
    1.96
    traj
    1.96
    WAY
    1.95
    Activations Density 0.058%

    No Known Activations