© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 4823
    Prev
    Next
    INDEX
    Explanations

    await, new, EditorGUILayout, Auto

    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
    А
    1.98
    ഹ്ലാദ
    1.84
    о
    1.80
    𝟰
    1.78
     estrogens
    1.71
     inaugur
    1.70
     inscri
    1.66
    да
    1.61
     durumu
    1.61
     welche
    1.60
    POSITIVE LOGITS
     물론
    2.00
     এছাড়াও
    1.74
    на
    1.69
    /=
    1.61
     consulate
    1.58
     groundwater
    1.52
    তে
    1.51
    etään
    1.51
     गौरतलब
    1.51
    ં
    1.50
    Activations Density 0.463%

    No Known Activations