© 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. 7109
    Prev
    Next
    INDEX
    Explanations

    qualities and characteristics

    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
     accepté
    1.06
     লক
    1.03
     워
    1.00
    新冠
    1.00
    curs
    0.95
     秦
    0.95
    erson
    0.93
     PROC
    0.93
     moderna
    0.93
    隍
    0.93
    POSITIVE LOGITS
    gend
    0.84
     hatches
    0.83
     happiest
    0.82
     metaphorical
    0.82
    adl
    0.82
     morphological
    0.81
     Bergh
    0.80
     fielder
    0.79
     arrhyth
    0.78
    aidh
    0.77
    Activations Density 0.000%

    No Known Activations