© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7111
    Prev
    Next
    INDEX
    Explanations

    job descriptions and postings

    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_22_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
     نفس
    0.95
     Oceanic
    0.85
    <0x95>
    0.85
     لہ
    0.81
     rebuttal
    0.79
    zelfde
    0.79
    讽
    0.79
    主に
    0.78
     select
    0.77
    同一个
    0.76
    POSITIVE LOGITS
    --(
    1.30
    PRNewswire
    1.10
    )--
    1.05
    .--
    1.05
    )—
    1.00
    STRA
    0.98
     (.)
    0.96
    ,--
    0.96
     ?-
    0.96
    .-(
    0.94
    Activations Density 0.041%

    No Known Activations