© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2079
    Prev
    Next
    INDEX
    Explanations

    inevitably, only, simply, predictably

    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
    ი
    0.96
     jedn
    0.95
     unu
    0.91
    ՞
    0.88
    šla
    0.88
    ঘ্র
    0.86
     آن‌ها
    0.86
    arccos
    0.85
    ன்கள்
    0.84
    者を
    0.83
    POSITIVE LOGITS
     ago
    1.15
    .$-
    1.11
     ('
    1.10
     onwards
    1.08
    为止
    1.08
    /'
    1.08
     ;)
    1.07
     Basement
    1.05
     Award
    1.03
     Λ
    1.03
    Activations Density 0.426%

    No Known Activations