© 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. 6273
    Prev
    Next
    INDEX
    Explanations

    heart problems and disease

    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
     répon
    1.96
    бина
    1.83
     percaya
    1.82
     retrouve
    1.78
     resultCode
    1.77
     dụng
    1.76
    롬
    1.76
     vuelta
    1.76
     filtra
    1.75
     pws
    1.75
    POSITIVE LOGITS
    synchronized
    0.78
    Git
    0.77
     Threat
    0.75
    threat
    0.74
    dire
    0.74
    Y
    0.74
    更高的
    0.69
    Se
    0.69
    icky
    0.67
     menacing
    0.65
    Activations Density 0.017%

    No Known Activations