© 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-65K
    7. 27396
    Prev
    Next
    INDEX
    Explanations

    technical requirements or explanations

    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_65k_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
     interés
    0.52
     lãi
    0.47
     Hyatt
    0.45
    віта
    0.45
     intérêt
    0.45
     кварти
    0.45
    મ
    0.44
     aans
    0.43
    lı
    0.43
    dun
    0.42
    POSITIVE LOGITS
    FormComponent
    0.45
    糟糕
    0.45
    性格
    0.43
     preponderance
    0.43
    狡
    0.41
     Navigator
    0.39
    TextBlock
    0.39
     극한
    0.39
     পরীক্ষা
    0.39
    Serialized
    0.39
    Activations Density 0.010%

    No Known Activations