© 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. 125536
    Prev
    Next
    INDEX
    Explanations

    experiencing pain

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

    concepts and lists

    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
    köz
    0.48
    Ser
    0.47
    inductive
    0.45
    صة
    0.45
    vertebr
    0.45
    崬
    0.45
    czyny
    0.45
    tw
    0.44
    ISATION
    0.44
    orsun
    0.43
    POSITIVE LOGITS
     players
    0.48
     dispara
    0.47
     to
    0.46
    }}^{\
    0.46
     друга
    0.45
     desafios
    0.45
     dificult
    0.43
     discrepancies
    0.43
     strada
    0.43
     playas
    0.43
    Activations Density 0.001%

    No Known Activations