© 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. 154339
    Prev
    Next
    INDEX
    Explanations

    Describes what comes after certain words

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

    deal with relationships

    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
     biodegrad
    0.52
    ዌ
    0.52
     Saty
    0.50
     Biswas
    0.50
     treacherous
    0.48
    äche
    0.48
     அவர்களை
    0.47
     smacked
    0.47
     tweeted
    0.47
     swayed
    0.47
    POSITIVE LOGITS
    Session
    0.47
    PRINT
    0.47
    Monter
    0.46
    Talk
    0.46
    PRODUCT
    0.46
    N
    0.46
    Happ
    0.45
    INSTR
    0.45
    谈
    0.45
    CIRCLE
    0.45
    Activations Density 0.001%

    No Known Activations