© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9020
    Prev
    Next
    INDEX
    Explanations

    frequency, repetition, counting

    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_40_width_16k_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
    i
    0.41
    ি
    0.39
    oons
    0.38
    ent
    0.38
    at
    0.37
     jt
    0.37
     পরবর্তী
    0.36
     claros
    0.35
    ாண
    0.35
    u
    0.35
    POSITIVE LOGITS
     подряд
    0.46
     razy
    0.45
    oleum
    0.45
    ље
    0.44
     fois
    0.43
     veces
    0.43
    不同的
    0.43
    ابي
    0.42
    ต่าง
    0.41
     steeply
    0.41
    Activations Density 0.060%

    No Known Activations