© 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. 12225
    Prev
    Next
    INDEX
    Explanations

    duration, key-value pairs

    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
    ᴰ
    2.09
    ਹੀਂ
    2.02
    ᵏ
    2.00
    laš
    1.93
    Ὁ
    1.92
    klär
    1.91
     intelekt
    1.89
    гласно
    1.86
     lek
    1.83
     skol
    1.82
    POSITIVE LOGITS
    ي
    2.45
    י
    2.34
    ی
    2.30
    ে
    2.11
    oqu
    2.08
    า
    2.03
    i
    1.88
    e
    1.87
    o
    1.84
    ი
    1.80
    Activations Density 0.002%

    No Known Activations