© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199499
    Prev
    Next
    INDEX
    Explanations

    basic features and types

    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
    ิ้น
    0.45
     Xinjiang
    0.44
     certificado
    0.44
     CDR
    0.44
    麗
    0.43
    стон
    0.43
     blinked
    0.42
    ڨ
    0.42
     coyote
    0.41
    㝒
    0.41
    POSITIVE LOGITS
     পর্যবেক্ষণ
    0.46
    ;
    0.45
    accur
    0.44
    to
    0.44
    ENGINE
    0.44
    acyjnych
    0.44
    अभ
    0.43
    vs
    0.43
     importants
    0.42
    endes
    0.42
    Activations Density 0.000%

    No Known Activations