© 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. 3088
    Prev
    Next
    INDEX
    Explanations

    titles starting with The

    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
    ㅐ
    0.92
     dlg
    0.89
    CAM
    0.89
    UY
    0.88
     meio
    0.85
    념
    0.81
    USU
    0.80
     xr
    0.80
    ifa
    0.80
    ikey
    0.79
    POSITIVE LOGITS
     Goodbye
    1.96
    titanic
    1.92
     Casablanca
    1.90
     Chinatown
    1.83
    艋
    1.80
     Farewell
    1.79
     Divorce
    1.78
     Casualty
    1.78
     Moonlight
    1.77
     Versailles
    1.77
    Activations Density 0.291%

    No Known Activations