© 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. 162235
    Prev
    Next
    INDEX
    Explanations

    Peninsula City, Students complain, down well

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

    adjusts or changes

    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
     chiedere
    0.49
     seguire
    0.48
    ERROR
    0.47
    2
    0.46
    attribute
    0.46
     भूले
    0.45
     parámetro
    0.45
    ERO
    0.45
     verdade
    0.45
     crave
    0.45
    POSITIVE LOGITS
     능
    0.46
    みを
    0.44
     antid
    0.43
     이를
    0.43
    껴
    0.43
     electricians
    0.42
    спе
    0.42
    ప్రత్య
    0.42
    軎
    0.42
     educational
    0.42
    Activations Density 0.001%

    No Known Activations