© 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. 2540
    Prev
    Next
    INDEX
    Explanations

    consulting doctors and specialists

    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
    duction
    2.02
     passwords
    2.01
     toner
    2.00
     baits
    1.97
    ortion
    1.87
     oxalic
    1.83
     disulfide
    1.82
    债
    1.82
     mineralization
    1.81
     passports
    1.81
    POSITIVE LOGITS
    intens
    0.67
    Obst
    0.63
    付属
    0.60
    循環
    0.59
     intens
    0.58
    眼里
    0.57
     practising
    0.57
     Vener
    0.56
     войск
    0.55
     obst
    0.55
    Activations Density 0.352%

    No Known Activations