© 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. 5710
    Prev
    Next
    INDEX
    Explanations

    closing signature

    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
     rispar
    1.10
     ホイールセット
    1.09
    шибка
    1.02
    Dies
    1.02
    eará
    1.01
    cnico
    0.99
    €™
    0.96
    ISR
    0.95
    eev
    0.94
     حوصل
    0.93
    POSITIVE LOGITS
    semantics
    1.68
    ложений
    1.53
    白い
    1.53
    ourced
    1.46
    ɕ
    1.46
    ible
    1.45
     mutate
    1.44
     conjunction
    1.42
     pink
    1.42
    magenta
    1.42
    Activations Density 0.084%

    No Known Activations