© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3858
    Prev
    Next
    INDEX
    Explanations

    handling security, healthy eating, starting slowly

    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
    gg
    1.15
    張
    1.14
    Hughes
    1.10
     Hagg
    1.09
     giocatore
    1.07
     spel
    1.06
    agh
    1.05
     Hughes
    1.05
     giocatori
    1.05
    owy
    1.04
    POSITIVE LOGITS
     necrotic
    1.17
    IDENTAL
    1.15
     Mortality
    1.13
     carcinogenic
    1.12
     neutralization
    1.12
    }.${
    1.09
     pathogenicity
    1.08
     CIV
    1.07
     dermatitis
    1.07
     biomark
    1.07
    Activations Density 0.123%

    No Known Activations