© 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. 5407
    Prev
    Next
    INDEX
    Explanations

    silence that

    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
    خه
    2.01
    τώ
    1.82
    ือง
    1.82
    SIBILITY
    1.80
    ivalence
    1.80
    到位
    1.79
    票
    1.77
    ื
    1.75
    attachment
    1.75
     AGAINST
    1.75
    POSITIVE LOGITS
     Niv
    0.76
     Dach
    0.68
    taj
    0.66
    組立
    0.65
     skar
    0.63
     Cutter
    0.61
    walla
    0.61
     Spur
    0.59
     ransom
    0.58
     Ched
    0.57
    Activations Density 0.013%

    No Known Activations