© 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. 52
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating direction or relation

    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
    1.55
     reckons
    1.45
    際は
    1.40
     速
    1.39
    𝒈
    1.39
     Announcements
    1.32
     Cumm
    1.32
     nets
    1.30
    oustache
    1.30
     voller
    1.29
    POSITIVE LOGITS
    to
    3.73
     to
    3.73
    To
    3.03
     к
    2.97
     الى
    2.85
     terhadap
    2.83
     đến
    2.74
     aos
    2.68
    tos
    2.64
    싶
    2.61
    Activations Density 0.923%

    No Known Activations