© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10486
    Prev
    Next
    INDEX
    Explanations

    rain

    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_13_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
     avian
    1.58
     dirig
    1.50
    jaar
    1.47
    𝕣
    1.45
     jaga
    1.45
     LW
    1.41
    Wind
    1.38
     hogy
    1.37
    ществ
    1.36
     κρα
    1.36
    POSITIVE LOGITS
    ゴム
    1.85
    техни
    1.78
    drop
    1.76
    missing
    1.68
    クセル
    1.65
    芑
    1.65
     Potenz
    1.63
    বহুল
    1.58
    बीन
    1.57
    nok
    1.57
    Activations Density 0.061%

    No Known Activations