© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 15247
    Prev
    Next
    INDEX
    Explanations

    which facilitate, & qualify, rest after

    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_16_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
     Gy
    0.54
     controvers
    0.52
    __)
    0.52
     речь
    0.51
     лиш
    0.50
     wry
    0.50
     каче
    0.49
     torment
    0.48
     ወ
    0.48
    Gy
    0.46
    POSITIVE LOGITS
    এ
    0.49
    える
    0.49
    드
    0.49
     organizations
    0.47
    为
    0.47
    database
    0.46
    参
    0.46
    ABLE
    0.46
     database
    0.46
    eper
    0.46
    Activations Density 0.000%

    No Known Activations