© 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. 14751
    Prev
    Next
    INDEX
    Explanations

    project creation

    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
    /'.$
    1.20
    Ammo
    1.13
    قوم
    1.10
    Writes
    1.07
    Nich
    1.07
    boor
    1.07
     Beaucoup
    1.07
    夆
    1.06
    WQ
    1.06
    hormat
    1.06
    POSITIVE LOGITS
     is
    1.03
     trivia
    1.01
     I
    0.96
     does
    0.94
     truth
    0.94
     І
    0.93
     mathematics
    0.92
     firstNumber
    0.91
     not
    0.90
     carcinoma
    0.90
    Activations Density 0.001%

    No Known Activations