© 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. 15-GEMMASCOPE-2-RES-16K
    7. 5772
    Prev
    Next
    INDEX
    Explanations

    slight variations between systems

    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
    tke
    1.25
    からです
    1.24
     satisfe
    1.20
     adrenalin
    1.20
    renaline
    1.19
    kla
    1.14
    ileged
    1.13
     phosphatidyl
    1.13
    უცი
    1.13
    POSITIVE LOGITS
    ["
    1.38
    abases
    1.35
     approximate
    1.35
     συνο
    1.34
    equalsIgnoreCase
    1.32
    ophora
    1.32
    ılarak
    1.31
    Descripcion
    1.31
    overall
    1.30
     gă
    1.30
    Activations Density 0.010%

    No Known Activations