© 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. 3010
    Prev
    Next
    INDEX
    Explanations

    clicking buttons and links

    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
    oving
    1.41
     qal
    1.37
    yscy
    1.37
    )}$
    1.35
    itchfield
    1.33
    opss
    1.33
    }}$
    1.33
    ienz
    1.32
    ensk
    1.30
    ouche
    1.29
    POSITIVE LOGITS
     button
    1.38
    photo
    1.33
     play
    1.31
     link
    1.30
     image
    1.27
     "
    1.27
    play
    1.26
     '
    1.25
     generate
    1.24
     images
    1.24
    Activations Density 0.135%

    No Known Activations