© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2128
    Prev
    Next
    INDEX
    Explanations

    she's, yes, or affirmative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     adjournment
    2.25
    佢
    2.21
    她在
    2.13
     instalments
    2.00
     (£
    1.99
     instalment
    1.97
    šit
    1.92
    ouncement
    1.92
    organiser
    1.91
     on
    1.90
    POSITIVE LOGITS
     obey
    2.12
     combust
    1.99
     объекты
    1.99
    rinsic
    1.97
     instinctively
    1.97
    req
    1.96
    츠
    1.92
     possesses
    1.90
     излу
    1.86
     respir
    1.86
    Activations Density 0.576%

    No Known Activations