© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9613
    Prev
    Next
    INDEX
    Explanations

    servicesdpemma

    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
    -,
    1.40
    \%,
    1.19
    eve
    1.16
    toolbox
    1.08
    +,
    1.08
    plotting
    1.08
    simulation
    1.07
    simulator
    1.07
    sort
    1.06
    weathermap
    1.04
    POSITIVE LOGITS
     ライ
    1.32
     '*')
    1.25
     británico
    1.24
     SIAM
    1.23
    റിൽ
    1.21
    如果您
    1.21
     Если
    1.21
    ські
    1.19
    貴
    1.19
    ラ
    1.19
    Activations Density 0.001%

    No Known Activations