© 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. 12862
    Prev
    Next
    INDEX
    Explanations

    replace with your

    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
     enfermedad
    1.15
     वस्तुओं
    1.09
     Государ
    1.06
     خارج
    1.06
     aumento
    1.04
     Coating
    1.04
    ]:
    1.04
     coating
    1.04
     రాజ్య
    1.03
     =$
    1.03
    POSITIVE LOGITS
    umoto
    1.17
    おすすめ
    1.10
    getNext
    1.10
    might
    1.10
     might
    1.09
    搞
    1.08
     desperately
    1.08
    FERENCES
    1.06
    ladi
    1.06
    epik
    1.06
    Activations Density 0.309%

    No Known Activations