© 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. 7396
    Prev
    Next
    INDEX
    Explanations

    narrow streets and charming places

    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
     biodiversity
    1.04
     Biodiversity
    1.00
     Aviation
    0.98
     अंड
    0.97
     Bekasi
    0.96
    Примітки
    0.93
    телям
    0.91
    冖
    0.91
     gorillas
    0.91
    subarray
    0.90
    POSITIVE LOGITS
     town
    1.25
     centrum
    1.19
     Ecusson
    1.16
     TOWN
    1.16
    Heart
    1.08
     Town
    1.06
     SQUARE
    1.05
     Square
    1.05
     square
    1.05
    Town
    1.05
    Activations Density 0.209%

    No Known Activations