© 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. 3556
    Prev
    Next
    INDEX
    Explanations

    that might

    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
     gonna
    1.59
     temperat
    1.51
    咁
    1.49
     alles
    1.46
     entier
    1.45
     everybody
    1.44
     wszystkich
    1.43
     gotta
    1.41
     tous
    1.41
     alot
    1.40
    POSITIVE LOGITS
    may
    1.55
     may
    1.44
    iarism
    1.38
    atamente
    1.32
     affirmatively
    1.31
     conceivably
    1.30
     inadvertently
    1.30
    "]).
    1.28
    eman
    1.27
    ilere
    1.27
    Activations Density 0.369%

    No Known Activations