© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3613
    Prev
    Next
    INDEX
    Explanations

    of the

    np_acts-logits-general · gemini-2.5-flash-lite

    originating from specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    );*/
    0.38
    antiate
    0.35
     অধ্য
    0.35
    はこの
    0.34
     seguenti
    0.34
    лянчук
    0.34
    ούς
    0.33
     ನಾನು
    0.33
    すなわち
    0.33
    ம்பிய
    0.32
    POSITIVE LOGITS
      
    0.49
     “
    0.45
     sorts
    0.41
     ”
    0.40
     controversial
    0.39
     Reuters
    0.39
    <0xC2>
    0.35
    &
    0.35
     Arten
    0.34
     disgruntled
    0.34
    Activations Density 0.331%

    No Known Activations