© 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. 11467
    Prev
    Next
    INDEX
    Explanations

    on-screen instructions

    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
     ดู
    1.56
    と言う
    1.54
     recursively
    1.53
    дации
    1.52
     болот
    1.51
    л
    1.50
     пакет
    1.47
    ได้
    1.47
     baixar
    1.47
     seguramente
    1.46
    POSITIVE LOGITS
    <bos>
    1.44
     Vict
    1.44
     enact
    1.43
    personality
    1.41
     misconduct
    1.37
     Deb
    1.35
    produksi
    1.34
    yesha
    1.33
     Leung
    1.32
     Heard
    1.31
    Activations Density 0.018%

    No Known Activations