© 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. 11970
    Prev
    Next
    INDEX
    Explanations

    code segments and structured formats

    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
     nuanced
    1.52
     intricate
    1.45
     ἔ
    1.43
     flawed
    1.36
    纰
    1.36
     slider
    1.35
     Gladiator
    1.35
     sī
    1.35
     compromised
    1.33
     Slider
    1.33
    POSITIVE LOGITS
     nazw
    1.21
    ternal
    1.13
    aad
    1.06
    بوت
    1.04
    aide
    1.04
    ادس
    1.03
    a
    1.03
    uus
    1.02
    чат
    1.01
     находиться
    1.00
    Activations Density 0.000%

    No Known Activations