© 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. 128357
    Prev
    Next
    INDEX
    Explanations

    protect Boo

    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
     silencio
    0.52
     recibieron
    0.47
     progressivement
    0.47
     bhij
    0.47
     dirig
    0.46
    чки
    0.45
     silenz
    0.45
    뎁
    0.45
     पाण
    0.45
     regal
    0.44
    POSITIVE LOGITS
    Ben
    0.46
    他和
    0.45
    នុស្ស
    0.45
    Yas
    0.45
    Maharashtra
    0.44
    暾
    0.43
    Shar
    0.43
    Exper
    0.43
    Working
    0.43
    Wheel
    0.43
    Activations Density 0.001%

    No Known Activations