© 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. 239460
    Prev
    Next
    INDEX
    Explanations

    listings or descriptions

    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
    aru
    0.54
    oreau
    0.50
    ټبال
    0.50
    Š
    0.50
    戦
    0.50
     totalement
    0.50
    Über
    0.49
    Цена
    0.49
    ája
    0.48
    =="
    0.48
    POSITIVE LOGITS
     contemplation
    0.47
     Clover
    0.44
     กัน
    0.43
     Cocker
    0.43
     her
    0.43
     at
    0.43
     discernment
    0.42
     clo
    0.42
     Kerm
    0.42
     QC
    0.42
    Activations Density 0.001%

    No Known Activations