© 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. 4892
    Prev
    Next
    INDEX
    Explanations

    flesh out

    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
    🫤
    1.27
     när
    1.09
    ☹
    1.08
     👌
    1.07
     provinc
    1.07
     😊
    1.05
     fm
    1.04
     lol
    1.03
    .]
    1.02
     :).
    1.02
    POSITIVE LOGITS
    down
    3.08
     down
    2.88
    together
    2.79
     together
    2.51
     aside
    2.39
     DOWN
    2.32
    Down
    2.30
    downs
    2.25
     forth
    2.21
     off
    2.20
    Activations Density 0.365%

    No Known Activations