© 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. 5396
    Prev
    Next
    INDEX
    Explanations

    best followed by practices or intentions

    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
    currentPlayer
    2.48
    ethylene
    2.23
    %$$
    2.17
     meritorious
    2.14
    Ή
    2.04
    paying
    2.04
    स्तिष्क
    1.97
     wee
    1.93
    pay
    1.93
    concern
    1.92
    POSITIVE LOGITS
    า
    4.02
    i
    3.74
    י
    3.44
    e
    3.41
    ್‌
    3.26
    a
    3.23
    ت
    3.22
    া
    3.09
    o
    3.08
    s
    3.08
    Activations Density 0.169%

    No Known Activations