© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10800
    Prev
    Next
    INDEX
    Explanations

    bouncing off surfaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     RE
    2.06
     DI
    1.94
     해외
    1.92
    ႉ
    1.92
     CE
    1.90
    궁
    1.89
     PCS
    1.87
    턴
    1.86
     FI
    1.85
     Uz
    1.84
    POSITIVE LOGITS
    vány
    2.04
     esperar
    1.93
    klop
    1.90
    enhuma
    1.89
     resalt
    1.85
    ômes
    1.83
    स्ताना
    1.79
    ográf
    1.79
     espectáculo
    1.78
    ór
    1.78
    Activations Density 0.005%

    No Known Activations