© 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. 128691
    Prev
    Next
    INDEX
    Explanations

    Vishnu and Mahabali stories

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

    deep breath, breaths, chance

    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
    ന്‍റെ
    0.45
    പ്പുറ
    0.44
     endearing
    0.43
     ремонт
    0.42
    Spectrum
    0.42
     பராம
    0.42
     spond
    0.42
    ט
    0.42
     preservar
    0.41
     upto
    0.41
    POSITIVE LOGITS
    :
    0.48
    ichever
    0.46
    othe
    0.45
    )}$
    0.42
    出来
    0.42
    othes
    0.41
     зале
    0.41
    也要
    0.41
    之下
    0.41
    ُوْ
    0.40
    Activations Density 0.002%

    No Known Activations