© 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. 11356
    Prev
    Next
    INDEX
    Explanations

    lifecycle stage, value, or hooks

    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
    es
    2.82
    ভাবেই
    2.61
    嵋
    2.57
    ﺕ
    2.57
    ">%
    2.56
    党委
    2.55
     gxf
    2.52
    ﻥ
    2.51
     tàu
    2.48
    nder
    2.47
    POSITIVE LOGITS
    ет
    2.90
    uoso
    2.88
    ਰੇ
    2.68
    uose
    2.59
    قوق
    2.53
    s
    2.52
    lng
    2.51
    ləşdirilib
    2.50
    ្សែ
    2.49
    সই
    2.49
    Activations Density 0.000%

    No Known Activations