© 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. 91247
    Prev
    Next
    INDEX
    Explanations

    occurred in

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

    data modification and validation

    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
     EACH
    0.51
     ಕೆಲವು
    0.47
    各
    0.45
     talvez
    0.44
    hopefully
    0.44
     российских
    0.43
    鋳
    0.43
    
    0.43
     Democratic
    0.42
     potencial
    0.42
    POSITIVE LOGITS
    这里
    0.46
     relocation
    0.44
     esso
    0.43
     died
    0.43
    *>
    0.43
     oscill
    0.42
     git
    0.42
     blasts
    0.41
     oscillator
    0.41
    熠
    0.41
    Activations Density 0.000%

    No Known Activations