© 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. 221930
    Prev
    Next
    INDEX
    Explanations

    compassion and hope

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

    resolutions and what to do next

    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
     exercitation
    0.50
     muškar
    0.50
    ф
    0.47
    っ
    0.46
    全長
    0.45
     avez
    0.44
    тпу
    0.43
     astronomy
    0.43
     জনসাধারণ
    0.43
     enclosing
    0.43
    POSITIVE LOGITS
     NUR
    0.45
     MILLER
    0.45
    ottest
    0.45
    Sul
    0.44
    일에
    0.44
     Berman
    0.43
     Rxd
    0.43
     Notch
    0.43
     FAT
    0.43
    Ⲙ
    0.43
    Activations Density 0.000%

    No Known Activations