© 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. 31-GEMMASCOPE-2-RES-262K
    7. 54081
    Prev
    Next
    INDEX
    Explanations

    but clauses

    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
    one
    0.48
    ті
    0.46
    total
    0.45
    solution
    0.44
    charging
    0.43
    a
    0.43
    they
    0.41
    ুখে
    0.41
     they
    0.41
    s
    0.41
    POSITIVE LOGITS
     ungef
    0.50
     détermine
    0.48
     పరీక్ష
    0.44
     Bibliothèque
    0.43
     Einführung
    0.42
    日本では
    0.41
     memeriksa
    0.41
     слегка
    0.40
    筛选
    0.40
     Geschmack
    0.40
    Activations Density 0.011%

    No Known Activations