© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109567
    Prev
    Next
    INDEX
    Explanations

    visit your local

    np_acts-logits-general · gemini-2.5-flash-lite

    word followed by a preposition or descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    َع
    0.51
     handicap
    0.51
     disconnecting
    0.49
     openness
    0.45
    َق
    0.45
     tooling
    0.43
    リー
    0.43
     endpoints
    0.43
     upfront
    0.43
     pallets
    0.43
    POSITIVE LOGITS
     הצ
    0.52
     देणे
    0.51
    譞
    0.50
     Juda
    0.49
     Более
    0.49
     दिर
    0.48
     Są
    0.48
     wyra
    0.47
     Cappadocia
    0.47
     μία
    0.46
    Activations Density 0.001%

    No Known Activations