© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 1761
    Prev
    Next
    INDEX
    Explanations

    confidante iterates

    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
    teilung
    1.29
    hotra
    1.20
    Tov
    1.16
    zych
    1.15
    殻
    1.10
    出现在
    1.10
    nuts
    1.09
    ucapkan
    1.08
    hurst
    1.08
    heder
    1.06
    POSITIVE LOGITS
     Intensity
    0.84
     pulmonary
    0.83
     chronic
    0.83
    +")
    0.82
    +')
    0.79
    polar
    0.77
    ana
    0.77
    ener
    0.76
    瑕
    0.76
    }}^{\
    0.74
    Activations Density 0.403%

    No Known Activations