© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1967
    Prev
    Next
    INDEX
    Explanations

    variable assignment

    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
     advertis
    1.54
    edio
    1.50
     relating
    1.50
     advertised
    1.47
     pertaining
    1.45
    <unused1008>
    1.43
    enterprise
    1.42
     جمل
    1.41
     of
    1.39
    <unused298>
    1.38
    POSITIVE LOGITS
     oğlu
    1.88
     ông
    1.81
     tàu
    1.78
     thậm
    1.77
     làng
    1.76
     tân
    1.76
     Cyril
    1.72
     haline
    1.67
     xưa
    1.66
     cùng
    1.66
    Activations Density 0.267%

    No Known Activations