© 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. 1361
    Prev
    Next
    INDEX
    Explanations

    sustainable future improvement

    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
    ~
    1.14
    engi
    1.07
    ـ
    1.05
    tom
    1.02
    Celestial
    1.01
     Sumer
    1.01
     Goliath
    0.99
     Celestial
    0.99
    tong
    0.99
    ャ
    0.98
    POSITIVE LOGITS
    정책
    1.62
     protección
    1.60
     policies
    1.56
     prevenir
    1.51
     alert
    1.48
     prevención
    1.46
     alerta
    1.45
    対策
    1.45
     legislación
    1.43
     preven
    1.42
    Activations Density 0.635%

    No Known Activations