© 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. 3094
    Prev
    Next
    INDEX
    Explanations

    IAM roles and policies

    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
    یف
    2.02
    په
    1.88
     munt
    1.87
    tain
    1.84
    ľov
    1.83
    taining
    1.82
    которые
    1.81
    𝕦
    1.76
    ei
    1.75
    TERY
    1.71
    POSITIVE LOGITS
    ┛
    2.33
     Directeur
    2.30
     "<<
    2.18
    sion
    2.15
     অফিস
    2.14
     Premio
    2.14
    比赛
    2.12
    ৩৬
    2.12
    ください
    2.11
    Counc
    2.11
    Activations Density 0.002%

    No Known Activations