© 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. 32243
    Prev
    Next
    INDEX
    Explanations

    notes and descriptive details

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

    anesthetist, cases, globally

    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
    sdag
    0.46
     aren
    0.45
    gay
    0.45
     સ્વ
    0.44
    ᆼ
    0.44
    隴
    0.43
     Etats
    0.43
    gang
    0.42
     período
    0.42
    excluded
    0.42
    POSITIVE LOGITS
    Compressed
    0.44
    Adapted
    0.42
    °
    0.42
    Slide
    0.41
    Stamped
    0.41
    ብዙ
    0.41
     یک
    0.40
    Carbon
    0.40
    Refrigerator
    0.40
    AC
    0.40
    Activations Density 0.000%

    No Known Activations