© 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. 10700
    Prev
    Next
    INDEX
    Explanations

    navigate to

    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
    สนใจ
    1.37
    รก
    1.35
    ดาว
    1.25
    อกาส
    1.12
    นน
    1.11
    กิน
    1.10
    ุปกรณ์
    1.09
    ฮ
    1.08
    новременно
    1.04
     เสียง
    1.04
    POSITIVE LOGITS
     predominantly
    1.60
     anatom
    1.56
     differentiates
    1.51
     cerebral
    1.50
     distinct
    1.49
     revolutionized
    1.48
     fundamentally
    1.46
     classed
    1.45
     hierarch
    1.45
     comparatively
    1.44
    Activations Density 0.281%

    No Known Activations