© 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. 244730
    Prev
    Next
    INDEX
    Explanations

    while the

    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
     Oleh
    0.49
    სი
    0.49
    нин
    0.47
    蟶
    0.45
    ksiyon
    0.44
    न
    0.44
     wheelchairs
    0.44
    ್ರಿ
    0.44
    വാ
    0.43
     unfriendly
    0.43
    POSITIVE LOGITS
     ውሃ
    0.44
     o
    0.43
    stub
    0.41
     коже
    0.41
     bán
    0.41
    皮
    0.41
     भीतर
    0.40
    >')
    0.40
    truncate
    0.39
     premise
    0.39
    Activations Density 0.001%

    No Known Activations