© 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. 204122
    Prev
    Next
    INDEX
    Explanations

    personalized ads and offers

    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
    </th>
    0.51
     Protok
    0.46
     Assistant
    0.44
     Settlement
    0.44
     Fot
    0.44
     Zaw
    0.44
     Dark
    0.43
     Unauthorized
    0.43
     Make
    0.43
     Dresden
    0.43
    POSITIVE LOGITS
    櫸
    0.52
    czas
    0.51
    approach
    0.50
    coeff
    0.49
    hygine
    0.48
    প
    0.48
    ഗു
    0.47
     gern
    0.47
     切り
    0.46
    Approach
    0.46
    Activations Density 0.004%

    No Known Activations