© 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. 3771
    Prev
    Next
    INDEX
    Explanations

    behavioral analysis

    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
    ness
    2.56
    뇰
    2.55
    رى
    2.54
    ਿਰ
    2.45
    discover
    2.44
    ∠
    2.40
    ⎛
    2.30
    一是
    2.29
    入手
    2.29
    shares
    2.29
    POSITIVE LOGITS
    ഹ
    2.78
    হারে
    2.77
     ଯ
    2.56
    ান
    2.50
     ທ
    2.36
     COLLISIONS
    2.35
    irut
    2.35
     EAR
    2.34
    ুম
    2.34
    ل
    2.31
    Activations Density 0.023%

    No Known Activations