© 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. 33492
    Prev
    Next
    INDEX
    Explanations

    copyright notices and company suffixes

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

    Facebook Meta Corporation Inc

    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
    льку
    0.53
     지난
    0.52
     Benutz
    0.52
    א
    0.52
     없음
    0.50
     கடந்த
    0.50
     ©️
    0.49
    暠
    0.49
     Fungsi
    0.48
    조건
    0.48
    POSITIVE LOGITS
     aldehydes
    0.42
     monarchs
    0.42
     multinationals
    0.41
    </h2>
    0.41
     corporates
    0.41
     suppliers
    0.40
     collectives
    0.40
    </h3>
    0.40
     vehicles
    0.40
     OEMs
    0.40
    Activations Density 0.001%

    No Known Activations