© 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. 209882
    Prev
    Next
    INDEX
    Explanations

    listing diverse topics

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

    garbled text, cream, or satellite

    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
    también
    0.46
    Ռ
    0.43
     enroll
    0.42
     CAS
    0.42
     Ú
    0.41
    Enroll
    0.41
    Ժ
    0.41
     satisfy
    0.41
    กระ
    0.40
    CAST
    0.40
    POSITIVE LOGITS
    ulk
    0.50
     kategor
    0.48
     kopi
    0.47
    fek
    0.46
     диску
    0.46
    ⾯
    0.46
    rek
    0.45
     nikdy
    0.45
     osk
    0.45
    rata
    0.45
    Activations Density 0.000%

    No Known Activations