© 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. 151210
    Prev
    Next
    INDEX
    Explanations

    decisions and involved

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

    technical terms and descriptors

    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
     congén
    0.55
     gratuits
    0.53
     plats
    0.52
     хоче
    0.51
    ،
    0.51
     mají
    0.50
     chce
    0.50
     comté
    0.49
     constat
    0.49
     должна
    0.48
    POSITIVE LOGITS
    m
    0.49
     annihilated
    0.48
    ותר
    0.47
    p
    0.47
    Founder
    0.46
    According
    0.46
    乔
    0.46
    n
    0.45
    Similar
    0.45
    ****/
    0.45
    Activations Density 0.001%

    No Known Activations