© 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. 8835
    Prev
    Next
    INDEX
    Explanations

    actions and states

    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
    ůli
    0.44
     महत्त्वा
    0.41
     প্রভৃতির
    0.39
    ifies
    0.38
    otional
    0.38
     స
    0.38
    ließlich
    0.38
    aughty
    0.37
     बात
    0.37
    itable
    0.37
    POSITIVE LOGITS
    :
    0.49
    8
    0.45
     with
    0.40
     apenas
    0.40
     rifer
    0.39
     aigus
    0.39
     only
    0.39
     siguen
    0.38
     equivalently
    0.38
     recordemos
    0.38
    Activations Density 0.275%

    No Known Activations