© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5075
    Prev
    Next
    INDEX
    Explanations

    which is heavier or bigger

    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
     sub
    0.94
    -
    0.93
    ,
    0.92
     modifica
    0.86
     anim
    0.80
     turn
    0.80
     que
    0.79
     prepara
    0.78
     emb
    0.77
     part
    0.74
    POSITIVE LOGITS
    Issuer
    1.42
    ኬ
    1.32
    上限
    1.31
     반지름
    1.31
    MaxLength
    1.31
    THRESHOLD
    1.31
    Globalization
    1.28
    Diameter
    1.27
    Bounded
    1.26
    Fitness
    1.25
    Activations Density 0.015%

    No Known Activations