© 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. 126907
    Prev
    Next
    INDEX
    Explanations

    accepts your, full tank, middle school

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

    demonstrating practical code

    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
    cd
    0.46
    endum
    0.44
    mathrm
    0.44
    си
    0.44
    brother
    0.43
    易
    0.43
    cam
    0.43
    rov
    0.43
    b
    0.43
    utory
    0.42
    POSITIVE LOGITS
     exhale
    0.59
     மாதிர
    0.57
    वालों
    0.54
     considere
    0.54
     orche
    0.52
     occupe
    0.51
     música
    0.50
     epigen
    0.50
     egiten
    0.50
    的孩子
    0.50
    Activations Density 0.001%

    No Known Activations