© 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. 105
    Prev
    Next
    INDEX
    Explanations

    start of a new turn

    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
    ouncement
    2.35
    をご覧ください
    2.31
    Organisation
    2.31
    などで
    2.30
     diarrhoea
    2.29
     biographer
    2.29
    佢
    2.28
     adjournment
    2.28
     (£
    2.26
     (’
    2.22
    POSITIVE LOGITS
    7
    2.42
     obey
    2.42
     emit
    2.41
     emits
    2.33
     permitt
    2.29
     constitut
    2.28
    8
    2.26
    rinsic
    2.26
     belong
    2.22
     combust
    2.21
    Activations Density 0.645%

    No Known Activations