© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81615
    Prev
    Next
    INDEX
    Explanations

    not fully released weights

    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
    碛
    0.49
    ักษณะ
    0.46
    فی
    0.45
    یکیشن
    0.44
    笕
    0.43
    acelet
    0.42
    ंजक
    0.42
    ื่น
    0.42
    کم
    0.41
    糗
    0.41
    POSITIVE LOGITS
     is
    0.49
     BUT
    0.44
     allows
    0.43
     লিখেছেন
    0.43
     позволяют
    0.42
     resear
    0.41
     సహ
    0.41
     allowing
    0.40
    逘
    0.40
     чрез
    0.40
    Activations Density 0.005%

    No Known Activations