© 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. 164244
    Prev
    Next
    INDEX
    Explanations

    instead of, getting sick, market, dreams

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

    anus expansion

    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
     pinion
    0.45
     Cros
    0.45
    s
    0.45
     Pon
    0.42
     Fisk
    0.42
    pon
    0.42
     ponies
    0.42
     vehicle
    0.41
     CNY
    0.41
    greencar
    0.41
    POSITIVE LOGITS
    ле
    0.50
    의
    0.47
     prostat
    0.47
     JsonSerializer
    0.46
     최고의
    0.46
     inflate
    0.46
     Temperaturen
    0.46
     étaient
    0.46
    때
    0.46
     najleps
    0.45
    Activations Density 0.000%

    No Known Activations