© 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. 13-GEMMASCOPE-2-RES-16K
    7. 6101
    Prev
    Next
    INDEX
    Explanations

    until proven

    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_13_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
    कुंठ
    2.93
    ാ
    2.06
     PIR
    2.05
     Pen
    2.04
     হারে
    2.01
     maqu
    1.98
    י
    1.97
    gouv
    1.97
    orate
    1.96
     உம்
    1.96
    POSITIVE LOGITS
    ৃহ
    2.13
    నికి
    2.08
    ್ರಾ
    2.07
    lacian
    2.05
    恢
    2.04
    ھار
    2.04
    ّر
    2.03
     reaching
    2.00
     reaches
    1.99
    ाइंड
    1.98
    Activations Density 0.162%

    No Known Activations