© 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. 11949
    Prev
    Next
    INDEX
    Explanations

    step-by-step instructions, questions, role-play prompts

    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
    K
    1.46
    с
    1.41
    С
    1.41
    К
    1.41
    Т
    1.41
    N
    1.40
    that
    1.37
    F
    1.35
    Khi
    1.34
    Ы
    1.34
    POSITIVE LOGITS
     is
    1.23
     biases
    1.14
     R
    1.09
     P
    1.08
     NDVI
    1.06
     covenants
    1.05
     ATMs
    1.05
     acoustics
    1.05
     belts
    1.04
     amortization
    1.04
    Activations Density 0.154%

    No Known Activations