© 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
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 6458
    Prev
    Next
    INDEX
    Explanations

    street and avenue names

    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
     instituto
    1.72
    atien
    1.46
    寄
    1.42
     extrap
    1.40
     abbey
    1.39
     vínculo
    1.36
    importDefault
    1.36
    +#+#
    1.35
     институт
    1.34
    招
    1.33
    POSITIVE LOGITS
    STE
    1.64
    suite
    1.54
     #
    1.43
    let
    1.41
    綻
    1.38
    floor
    1.37
     גדול
    1.35
    ste
    1.32
     peint
    1.31
    suites
    1.31
    Activations Density 0.047%

    No Known Activations