© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3614
    Prev
    Next
    INDEX
    Explanations

    stretching workout

    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_7_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
    čí
    2.77
     говорится
    2.53
    వలం
    2.36
    مله
    2.35
     '/',
    2.27
    ంచెం
    2.27
    ೋಟ
    2.25
    мия
    2.25
    뗑
    2.24
     любых
    2.23
    POSITIVE LOGITS
    ară
    2.11
    όμε
    1.94
    কর
    1.91
    ələ
    1.90
     enclose
    1.89
    टने
    1.86
    ্যা
    1.86
     내
    1.84
     செ
    1.82
    áférés
    1.79
    Activations Density 0.075%

    No Known Activations