© 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. 19875
    Prev
    Next
    INDEX
    Explanations

    narrative contexts

    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
    OSA
    0.50
    '
    0.43
    ABIL
    0.42
    DataAnnotations
    0.39
    Bij
    0.38
    https
    0.38
    OF
    0.38
    I
    0.38
    Avant
    0.37
     вла
    0.36
    POSITIVE LOGITS
     wymag
    0.54
     rescue
    0.52
     childhood
    0.50
     escape
    0.50
    forschungs
    0.50
     autrefois
    0.50
    រួ
    0.49
     ছুটে
    0.49
    ienne
    0.49
     инфек
    0.49
    Activations Density 0.010%

    No Known Activations