© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1035
    Prev
    Next
    INDEX
    Explanations

    code blocks and conditional logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-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
     Barth
    0.87
     nn
    0.85
     Acc
    0.81
    TT
    0.78
    api
    0.77
    ap
    0.76
    공
    0.75
    **
    0.73
    fa
    0.72
    nn
    0.72
    POSITIVE LOGITS
     mydict
    1.24
    xis
    1.21
    PayPal
    1.20
    keley
    1.18
    ้อย
    1.15
    Izq
    1.15
     ibuprofen
    1.13
    conclusion
    1.11
     осигурање
    1.09
     \|_{
    1.09
    Activations Density 0.437%

    No Known Activations