© 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. 14104
    Prev
    Next
    INDEX
    Explanations

    quantifying quantities, sequences, or series

    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
    rsvp
    1.31
    ersburg
    1.31
     인생
    1.30
    yong
    1.30
    dain
    1.30
     Shui
    1.27
     bewildered
    1.27
    嚷
    1.27
     lovers
    1.25
    вале
    1.25
    POSITIVE LOGITS
     augmenté
    1.16
     +
    1.13
     stärker
    1.11
     aanv
    1.03
    后续
    1.02
     crescere
    1.01
    Expansion
    1.00
     tillegg
    1.00
     diferencial
    0.98
     Ensuite
    0.97
    Activations Density 0.000%

    No Known Activations