© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14618
    Prev
    Next
    INDEX
    Explanations

    hybrid systems and models

    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_13_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
     또는
    1.59
     및
    1.58
    alogical
    1.57
    ological
    1.54
    iversity
    1.53
     或
    1.50
    orms
    1.49
    或
    1.49
    analytic
    1.47
     的
    1.46
    POSITIVE LOGITS
     bloqueo
    1.94
     verrou
    1.83
     espalda
    1.78
     pausa
    1.74
     gadis
    1.67
     daño
    1.67
     aonde
    1.66
     dietro
    1.66
     desblo
    1.66
     pagare
    1.65
    Activations Density 0.043%

    No Known Activations