© 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. 248671
    Prev
    Next
    INDEX
    Explanations

    season or time

    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
     gro
    0.53
    dv
    0.52
     winter
    0.50
     dv
    0.49
     mason
    0.49
     cook
    0.47
     đ
    0.46
     larc
    0.45
     ظ
    0.45
     monitor
    0.45
    POSITIVE LOGITS
     அரசின்
    0.50
    лго
    0.48
    PLAYS
    0.47
    oshin
    0.47
     açúcar
    0.45
     সিস্ট
    0.45
    PPAR
    0.45
     उत्पादन
    0.44
     proclaims
    0.44
    irectional
    0.44
    Activations Density 0.001%

    No Known Activations