© 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. 179223
    Prev
    Next
    INDEX
    Explanations

    selling tickets

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

    simple, easier, revealed information

    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
    アルバム
    0.47
     সুখী
    0.46
     হতা
    0.46
    ][
    0.44
    กัน
    0.43
     ভালবাস
    0.43
    ერი
    0.42
     amistad
    0.41
    리
    0.41
    ुक
    0.40
    POSITIVE LOGITS
    orbent
    0.45
     Pavia
    0.45
    emis
    0.44
     சென்னைய
    0.43
     mínimos
    0.42
     bioactive
    0.41
    geo
    0.41
    Bio
    0.41
    emitting
    0.41
    ఫో
    0.40
    Activations Density 0.002%

    No Known Activations