© 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. 161400
    Prev
    Next
    INDEX
    Explanations

    earlier than you

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

    concepts and terms

    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
     ministerial
    0.51
    oc
    0.47
    ᱾
    0.46
     uniquely
    0.46
    scoreboard
    0.46
     keenly
    0.44
     repaid
    0.44
     diverse
    0.44
     rare
    0.43
    facing
    0.43
    POSITIVE LOGITS
    🎨
    0.48
     Carly
    0.48
     রাস্তায়
    0.48
     Afghans
    0.46
     Kaye
    0.46
     Teg
    0.46
     Projected
    0.46
     október
    0.45
     Apartments
    0.45
     худож
    0.45
    Activations Density 0.002%

    No Known Activations