© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 33471
    Prev
    Next
    INDEX
    Explanations

    any language

    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
     Occupational
    0.42
     eggs
    0.41
    ంగ్
    0.40
     Eggs
    0.40
     Accreditation
    0.40
    вания
    0.39
    Careers
    0.39
    콥
    0.39
    Eggs
    0.39
    ции
    0.38
    POSITIVE LOGITS
     qualsiasi
    0.52
     যেকোন
    0.50
     dowol
    0.48
     fanatic
    0.48
    čiu
    0.48
     няко
    0.47
     qualquer
    0.47
     اختیار
    0.47
     queste
    0.47
     liquido
    0.46
    Activations Density 0.003%

    No Known Activations