© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12400
    Prev
    Next
    INDEX
    Explanations

    content rules exploit devices

    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
    ラー
    1.05
    繫
    1.03
    생
    1.00
    нутри
    0.99
    FileInput
    0.98
    "]
    0.97
    する
    0.97
    res
    0.95
    ラ
    0.95
     maneras
    0.94
    POSITIVE LOGITS
     fluence
    1.31
     obstructing
    1.29
     intoxicated
    1.27
     sung
    1.25
     exit
    1.23
     abrupt
    1.21
     shutting
    1.19
     impeding
    1.19
     glare
    1.18
     melatonin
    1.17
    Activations Density 0.000%

    No Known Activations