© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4361
    Prev
    Next
    INDEX
    Explanations

    think of it

    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
    এবং
    1.17
    ה
    1.09
    AND
    1.02
    رت
    1.02
    ا
    0.99
    ă
    0.98
    ዴት
    0.97
    लपुर
    0.97
    Creo
    0.96
     twenties
    0.96
    POSITIVE LOGITS
    iation
    0.98
     (
    0.97
     are
    0.95
     may
    0.93
    </h3>
    0.90
     is
    0.89
     fulfil
    0.89
     Rawls
    0.89
     været
    0.88
    ेश
    0.87
    Activations Density 0.409%

    No Known Activations