© 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. 20932
    Prev
    Next
    INDEX
    Explanations

    discuss the

    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
     U
    0.46
     Id
    0.44
     ഞാൻ
    0.42
     Obama
    0.42
     PO
    0.41
     அடித்த
    0.41
    我想
    0.41
     grandkids
    0.41
     Love
    0.40
     الهدف
    0.40
    POSITIVE LOGITS
    шаем
    0.44
     abiotic
    0.38
    堷
    0.38
    ushman
    0.37
     barbit
    0.37
    ื่อ
    0.37
    elte
    0.37
     physico
    0.36
    轵
    0.36
     throughout
    0.36
    Activations Density 0.001%

    No Known Activations