© 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. 1743
    Prev
    Next
    INDEX
    Explanations

    sports game nouns

    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
    ̫
    1.24
    bella
    1.20
    ται
    1.18
     ";"
    1.17
    𝒹
    1.17
    nement
    1.16
    นะคะ
    1.11
    emberg
    1.11
    𝓉
    1.07
     (#{
    1.06
    POSITIVE LOGITS
     visiteurs
    1.41
    visitors
    1.33
     יכול
    1.31
     visitors
    1.26
    owls
    1.25
    鄒
    1.24
     dispoz
    1.23
    inez
    1.22
     trám
    1.20
     visitantes
    1.20
    Activations Density 0.426%

    No Known Activations