© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126687
    Prev
    Next
    INDEX
    Explanations

    STCM and brands

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

    broad, conceptual thinking and resources

    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_31_width_262k_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
     ອ
    0.50
     شرطونه
    0.48
     früheren
    0.47
    ਮੀ
    0.47
    ږئ
    0.46
    ərb
    0.46
    ສົ່ງ
    0.46
    wami
    0.46
     कुशलता
    0.46
    효
    0.46
    POSITIVE LOGITS
    i
    0.57
    ى
    0.52
     Chaucer
    0.49
    Went
    0.49
    x
    0.48
     Wedgwood
    0.46
    ​
    0.46
    N
    0.46
     n
    0.45
     Shakespeare
    0.45
    Activations Density 0.000%

    No Known Activations