© 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. 12-GEMMASCOPE-2-RES-16K
    7. 5186
    Prev
    Next
    INDEX
    Explanations

    an open AI

    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
    ensuremath
    1.57
    jala
    1.47
    这一点
    1.41
    𝓪
    1.30
    DECL
    1.30
     pyramidal
    1.30
    Parser
    1.28
     comen
    1.27
    جد
    1.25
     skriver
    1.24
    POSITIVE LOGITS
    adera
    1.47
    笠
    1.40
    atorium
    1.39
    ibility
    1.34
    rze
    1.33
    affordable
    1.32
     FAU
    1.30
    Shea
    1.30
    odge
    1.28
    yzed
    1.26
    Activations Density 0.001%

    No Known Activations