© 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. 404
    Prev
    Next
    INDEX
    Explanations

    0 or numbers

    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
    enty
    1.45
    expanding
    1.40
    istica
    1.32
    榈
    1.31
    istico
    1.29
    Expanding
    1.24
    audience
    1.23
    ```{
    1.23
     Extended
    1.22
     expansions
    1.21
    POSITIVE LOGITS
    xFF
    2.24
    xff
    1.80
    xffff
    1.71
    0
    1.70
    ciende
    1.69
    dain
    1.67
    ️⃣
    1.66
     uur
    1.66
     intervent
    1.64
    xFFFF
    1.62
    Activations Density 0.426%

    No Known Activations