© 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. 14813
    Prev
    Next
    INDEX
    Explanations

    global scale or individual level

    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
    る
    1.34
    ETHER
    1.23
    させて頂
    1.21
    FER
    1.19
    (""))
    1.18
    jz
    1.17
    けない
    1.15
    ICSS
    1.14
    ר
    1.13
    Nonnull
    1.13
    POSITIVE LOGITS
     والص
    1.11
     lengkap
    1.05
     وب
    1.03
     plis
    1.03
     tegas
    1.00
     sikap
    1.00
     pendapat
    1.00
     Punto
    0.99
     appreci
    0.95
     simile
    0.94
    Activations Density 0.032%

    No Known Activations