© 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. 7995
    Prev
    Next
    INDEX
    Explanations

    numerical operations and errors

    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
    ้ง
    0.37
    穷
    0.36
    াস্থ্যের
    0.36
     syphilit
    0.35
    跏
    0.35
     payment
    0.34
    ставка
    0.34
    Questa
    0.34
    runken
    0.34
    Ꭳ
    0.34
    POSITIVE LOGITS
     الذين
    0.44
    ISE
    0.40
     Founding
    0.38
    }
    0.38
     Num
    0.37
     who
    0.37
     যারা
    0.36
     numérica
    0.36
    Prove
    0.36
    }\
    0.35
    Activations Density 0.001%

    No Known Activations