© 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. 25466
    Prev
    Next
    INDEX
    Explanations

    cell or cellular contexts

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

    cell or Text HOME

    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
    سی
    0.73
    কে
    0.71
    σα
    0.69
    ರ
    0.68
    ก
    0.67
     ಕಂಚ
    0.67
    ರವಾಗಿ
    0.66
    in
    0.66
    י
    0.65
    വ
    0.65
    POSITIVE LOGITS
     cell
    1.16
     Cell
    1.07
     Cells
    1.06
     cells
    1.05
    1.05
    Cell
    1.02
    Cells
    1.02
     세포
    0.96
     hücre
    0.89
     celular
    0.88
    Activations Density 0.019%

    No Known Activations