© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2914
    Prev
    Next
    INDEX
    Explanations

    in [location/possessive]

    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
    猾
    1.86
    ائع
    1.72
    砧
    1.70
    hebung
    1.70
     observables
    1.66
     lồ
    1.65
     bukti
    1.65
    嚏
    1.65
    テム
    1.62
    宵
    1.62
    POSITIVE LOGITS
    elia
    0.85
    onka
    0.82
     Bowie
    0.79
    arc
    0.79
     שכ
    0.79
     hud
    0.78
     communaut
    0.77
    wounded
    0.77
     τραγ
    0.77
     Morales
    0.76
    Activations Density 0.275%

    No Known Activations