© 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. 13-GEMMASCOPE-2-RES-16K
    7. 15464
    Prev
    Next
    INDEX
    Explanations

    nature.com/articles/

    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_13_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
    })"
    0.73
     понятно
    0.73
     mauvais
    0.69
    mas
    0.67
     самоу
    0.65
     നല്ല
    0.64
     cuando
    0.63
     quando
    0.63
     когда
    0.62
    प्रिय
    0.62
    POSITIVE LOGITS
     transformasi
    1.02
    ⚙
    1.01
    მასრულ
    1.01
     Transforming
    1.00
     Delight
    0.98
    outen
    0.96
     송
    0.96
    APR
    0.95
     elastomer
    0.95
     cargoes
    0.94
    Activations Density 0.001%

    No Known Activations