© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7009
    Prev
    Next
    INDEX
    Explanations

    guessing or "guess"

    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
     striées
    1.80
     dentées
    1.80
    ا
    1.50
     buoni
    1.49
     décrites
    1.48
    ް
    1.46
    ം
    1.44
     alcuna
    1.43
    ૂર્ણ
    1.35
    Dü
    1.35
    POSITIVE LOGITS
    ت
    1.45
     (
    1.41
    ول
    1.23
     reen
    1.23
    ,
    1.22
    س
    1.22
     Cele
    1.21
     cheque
    1.20
    ని
    1.18
     eCommerce
    1.18
    Activations Density 0.001%

    No Known Activations