© 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. 11411
    Prev
    Next
    INDEX
    Explanations

    structured lists and definitions

    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
    ാനാ
    1.02
     Dek
    1.02
     Interessen
    1.00
     Scales
    0.99
     N
    0.98
     Defensa
    0.98
     Table
    0.95
     A
    0.95
    A
    0.94
    אם
    0.93
    POSITIVE LOGITS
    glightbox
    1.51
     actuator
    1.46
    wellery
    1.45
     cosplay
    1.42
    eryka
    1.42
    oldown
    1.41
     emoticon
    1.41
    <unused988>
    1.41
     airbag
    1.40
     minecraft
    1.39
    Activations Density 0.001%

    No Known Activations