© 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. 11635
    Prev
    Next
    INDEX
    Explanations

    like or echoed

    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
     Del
    1.63
     At
    1.61
     Sul
    1.61
     Gal
    1.56
     An
    1.46
    an
    1.44
     Bal
    1.44
     I
    1.40
     prism
    1.35
     San
    1.34
    POSITIVE LOGITS
    䛺
    2.33
    㣫
    2.25
    㖩
    2.24
    㓦
    2.22
    晎
    2.20
    傃
    2.16
    市镇
    2.15
    敨
    2.12
     vucc
    2.12
    LevelLinking
    2.11
    Activations Density 0.071%

    No Known Activations