© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3583
    Prev
    Next
    INDEX
    Explanations

    unwavering belief, confident self, vibrant hue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     Manu
    1.32
     Bowen
    1.23
    ونة
    1.21
     eBooks
    1.18
    พิเศษ
    1.17
    ÉN
    1.15
     Kaf
    1.14
    ⁂
    1.12
     especific
    1.10
     Books
    1.10
    POSITIVE LOGITS
     dimost
    0.96
     trow
    0.95
    sterdam
    0.90
     arrondissement
    0.90
    盅
    0.89
    spr
    0.89
     اظہار
    0.89
     goû
    0.86
     représentants
    0.86
     proclamation
    0.86
    Activations Density 0.241%

    No Known Activations