© 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. 98007
    Prev
    Next
    INDEX
    Explanations

    complementary therapies

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

    I can, I need, I want

    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
    emento
    0.47
    WindowEvent
    0.45
    amey
    0.44
    ότερα
    0.44
     qnt
    0.44
    গর
    0.43
    ယ်
    0.42
    스
    0.42
    crm
    0.42
     একবার
    0.42
    POSITIVE LOGITS
     वर
    0.44
     EJ
    0.43
     выда
    0.41
     ح
    0.41
     Muslims
    0.41
    стта
    0.41
    iffs
    0.40
     AOS
    0.40
     צ
    0.40
    㞔
    0.40
    Activations Density 0.001%

    No Known Activations