© 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. 27004
    Prev
    Next
    INDEX
    Explanations

    phrase or description of subsequent words

    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
     কিন
    0.48
     được
    0.47
     купи
    0.42
    ㇁
    0.41
    蜮
    0.41
     পেই
    0.40
     титу
    0.40
    হই
    0.39
     pozit
    0.38
     поста
    0.38
    POSITIVE LOGITS
     ((
    0.39
     shorthand
    0.38
     álgebra
    0.37
     blight
    0.36
    Slf
    0.36
     QString
    0.35
     |
    0.35
     (!
    0.35
     bialgebras
    0.35
    oles
    0.35
    Activations Density 0.011%

    No Known Activations