© 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. 6204
    Prev
    Next
    INDEX
    Explanations

    Robert followed by surname

    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
    ɓ
    1.87
    نت
    1.82
     dô
    1.77
     رنز
    1.76
     zrozum
    1.74
    ния
    1.70
    rw
    1.68
     پژوه
    1.68
    引起
    1.67
    malar
    1.66
    POSITIVE LOGITS
    preuves
    1.45
     bondage
    1.18
    剤
    1.07
    Silent
    0.98
    Anno
    0.98
    obaan
    0.98
    clock
    0.96
    SUFFIX
    0.96
     beset
    0.95
    FECT
    0.94
    Activations Density 0.016%

    No Known Activations