© 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. 88814
    Prev
    Next
    INDEX
    Explanations

    for ... limited; precedes dinner

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

    group or transform data

    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
    ă
    0.47
    nek
    0.46
    dimensions
    0.46
    ometry
    0.44
     पचास
    0.44
    ıt
    0.44
     Ted
    0.43
     Entropy
    0.43
     Elys
    0.42
    es
    0.42
    POSITIVE LOGITS
     통해
    0.50
     give
    0.48
     broaden
    0.47
    ल्डेन
    0.47
    購
    0.47
     subscribe
    0.46
    🚗
    0.46
     hike
    0.46
     take
    0.46
     swap
    0.45
    Activations Density 0.000%

    No Known Activations