© 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. 94769
    Prev
    Next
    INDEX
    Explanations

    Explorer Edition

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

    topics and their definitions

    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
     馬
    0.58
    unam
    0.52
    omenclature
    0.50
    ходження
    0.48
    𝘃
    0.47
     ڈ
    0.46
    ess
    0.45
    ವಾರು
    0.45
    vah
    0.44
    amalla
    0.44
    POSITIVE LOGITS
     inferiores
    0.52
     cadena
    0.50
     жена
    0.50
     offert
    0.49
     prisión
    0.48
    किल
    0.47
     político
    0.47
    حول
    0.47
    捒
    0.47
    之地
    0.46
    Activations Density 0.000%

    No Known Activations