© 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. 91609
    Prev
    Next
    INDEX
    Explanations

    library

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

    GitHub README

    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
    ቅ
    0.42
    academy
    0.42
    iterranean
    0.41
    bär
    0.41
    registrar
    0.41
    uddho
    0.40
    𝗙
    0.40
     måste
    0.40
     academies
    0.40
     Andalusia
    0.40
    POSITIVE LOGITS
     github
    0.45
     readme
    0.45
     głównie
    0.44
     caveat
    0.44
     GitHub
    0.43
     LICENSE
    0.42
     grim
    0.41
     [])
    0.41
     ***
    0.41
     gracias
    0.40
    Activations Density 0.042%

    No Known Activations