© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 139328
    Prev
    Next
    INDEX
    Explanations

    action or completed states

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

    actions and completion

    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
    Ĩ
    0.45
    neutron
    0.44
    Kob
    0.41
    Nú
    0.40
    devtools
    0.40
     Guardia
    0.39
    tern
    0.39
     flog
    0.38
     गौर
    0.38
    loads
    0.38
    POSITIVE LOGITS
    帏
    0.39
    вале
    0.37
     અહીં
    0.37
    нице
    0.37
    ಿದೆ
    0.37
     اگ
    0.37
     মিলে
    0.36
     исследова
    0.35
     Sherry
    0.35
     ভাব
    0.35
    Activations Density 0.034%

    No Known Activations