© 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. 195047
    Prev
    Next
    INDEX
    Explanations

    safely, saving, channels, value

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

    dreams, fiction, imagination

    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
    ﺴ
    0.50
    大
    0.49
    ට
    0.48
     sécur
    0.47
    Attrition
    0.46
    ští
    0.46
     Pius
    0.45
    Implement
    0.45
    발
    0.44
    Several
    0.44
    POSITIVE LOGITS
    urazione
    0.49
     girlfriend
    0.47
    eken
    0.46
    ibi
    0.45
     anam
    0.45
    ane
    0.44
     அமைந்து
    0.44
    iraan
    0.44
     connecting
    0.43
     lubrication
    0.42
    Activations Density 0.002%

    No Known Activations