© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 12228
    Prev
    Next
    INDEX
    Explanations

    words starting with a specific letter

    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
     handover
    1.00
    tain
    1.00
     tyre
    0.98
    tis
    0.97
    ceres
    0.96
     scepticism
    0.95
    :-
    0.95
    localisation
    0.93
    metre
    0.93
    submit
    0.93
    POSITIVE LOGITS
    ופן
    1.14
    producto
    1.09
    Whitney
    1.06
    resión
    1.06
    炡
    1.05
    ÃO
    1.05
     Paradis
    1.04
    ровой
    1.03
     Pennington
    1.03
    Proven
    1.02
    Activations Density 0.010%

    No Known Activations