© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 93432
    Prev
    Next
    INDEX
    Explanations

    specific term followed by qualifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ~~
    0.56
     юк
    0.52
     เ
    0.50
    United
    0.48
     жер
    0.48
     Koš
    0.47
     ເ
    0.46
     ф
    0.46
     కో
    0.46
    Gü
    0.44
    POSITIVE LOGITS
    enroll
    0.53
    et
    0.50
    ovir
    0.49
    asibility
    0.48
    mag
    0.47
    ení
    0.47
    oul
    0.47
    optimizer
    0.47
    ní
    0.46
    oj
    0.46
    Activations Density 0.000%

    No Known Activations