© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5711
    Prev
    Next
    INDEX
    Explanations

    reducing size and memory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     drained
    0.82
     Белару
    0.67
     sheared
    0.65
     অস্থায়ী
    0.64
     yağ
    0.64
    Berat
    0.64
    拆
    0.63
    山
    0.63
    чается
    0.63
     pesc
    0.62
    POSITIVE LOGITS
     টেব
    0.68
     tabela
    0.68
     télé
    0.67
     Veh
    0.65
    还是很
    0.64
     TV
    0.64
    ovní
    0.64
    텔
    0.63
    헥
    0.62
    rinsic
    0.61
    Activations Density 0.056%

    No Known Activations