© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3504
    Prev
    Next
    INDEX
    Explanations

    conditional clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    updateOne
    1.47
     Collectors
    1.45
     attention
    1.35
     destaque
    1.33
     ovu
    1.31
    になっています
    1.29
    でしたが
    1.29
    お
    1.29
    所以在
    1.29
     types
    1.26
    POSITIVE LOGITS
     unwittingly
    1.55
    ôt
    1.52
     buộc
    1.45
    APK
    1.45
    altz
    1.43
    fusc
    1.39
     inconvenient
    1.34
     jeopard
    1.34
     zor
    1.32
     собственных
    1.31
    Activations Density 0.188%

    No Known Activations