© 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. 6609
    Prev
    Next
    INDEX
    Explanations

    synapses, synonyms, synfire, synergy

    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
    بيض
    1.33
    離島
    1.28
     wèi
    1.25
    ilevel
    1.24
     mortal
    1.21
     infus
    1.21
    ọng
    1.20
     "-"]
    1.20
     columnName
    1.20
    yczny
    1.19
    POSITIVE LOGITS
    anigans
    1.10
    aggregated
    1.09
    Bk
    1.08
    صول
    1.04
    ピソード
    1.02
    yskland
    1.02
    porter
    1.00
    sembles
    0.99
    ectady
    0.98
    боре
    0.98
    Activations Density 0.172%

    No Known Activations