© 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. 7696
    Prev
    Next
    INDEX
    Explanations

    saving code as .py or .php files

    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
    Emitter
    0.87
    走的
    0.82
     FontFamily
    0.81
    칭
    0.80
    Hochspringen
    0.80
    藤
    0.78
    윰
    0.76
     발
    0.75
     fø
    0.74
    AutoScaleMode
    0.74
    POSITIVE LOGITS
     PB
    1.09
     групп
    1.05
     Teams
    1.04
     INTEGER
    1.04
     DEC
    1.03
    試
    1.03
     TD
    1.03
     ATR
    1.02
     plex
    1.02
    Teams
    1.02
    Activations Density 0.105%

    No Known Activations