© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3099
    Prev
    Next
    INDEX
    Explanations

    truths and results

    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_15_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
     temsil
    1.43
     ジャン
    1.41
     GV
    1.39
     기자
    1.39
     değerli
    1.39
    ograf
    1.38
    proguard
    1.37
     베
    1.34
     Halb
    1.33
    𝐏
    1.32
    POSITIVE LOGITS
    ↵
    1.51
    nonsense
    1.25
    換え
    1.17
    aille
    1.09
     cases
    1.07
    нэт
    1.07
     ages
    1.07
    rear
    1.05
     conclusively
    1.04
     benar
    1.04
    Activations Density 0.008%

    No Known Activations