© 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. 126459
    Prev
    Next
    INDEX
    Explanations

    Ski Cross World Cup, Panel Discussion, artists

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

    how much

    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
     प्ले
    0.60
     应
    0.55
     nếu
    0.54
     nhưng
    0.53
     Quadrupèdes
    0.52
     দূতাবাস
    0.52
     dacă
    0.52
     đội
    0.51
     अनलि
    0.51
     儿童
    0.51
    POSITIVE LOGITS
     barrels
    0.50
    SU
    0.46
    以
    0.45
    NA
    0.45
     intersection
    0.45
    DESC
    0.44
    MU
    0.43
     och
    0.43
     orbits
    0.43
    ARIES
    0.43
    Activations Density 0.000%

    No Known Activations