© 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. 48044
    Prev
    Next
    INDEX
    Explanations

    technical terms and punctuation

    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
    入
    0.50
     ni
    0.48
    스
    0.48
    别
    0.47
     recruiter
    0.46
    是
    0.45
    偷
    0.45
     demostrado
    0.45
     mueve
    0.45
    “
    0.44
    POSITIVE LOGITS
    attha
    0.47
    പറ
    0.46
    itale
    0.44
    ifiziert
    0.44
    venuti
    0.42
    inati
    0.42
     instantiation
    0.42
     ইনস্টি
    0.41
    ocent
    0.41
    inst
    0.41
    Activations Density 0.001%

    No Known Activations