© 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. 10574
    Prev
    Next
    INDEX
    Explanations

    what is happening or being

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

    what's on/going/in

    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
    *
    0.46
    ;
    0.46
     одну
    0.43
    م
    0.43
    Means
    0.43
     Means
    0.42
    quoting
    0.41
    ",
    0.40
    如果你
    0.40
    :
    0.40
    POSITIVE LOGITS
    astă
    0.60
     happening
    0.57
     sucedió
    0.52
     açı
    0.51
     gebe
    0.51
     está
    0.50
     happens
    0.50
     commandant
    0.50
     lemak
    0.50
     féidir
    0.50
    Activations Density 0.133%

    No Known Activations