© 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. 57371
    Prev
    Next
    INDEX
    Explanations

    guaranteed delivery administrative financial

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

    leadership, authority, recognition

    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
    🧠
    0.50
    brain
    0.47
    ћин
    0.45
    Elf
    0.45
     Brain
    0.45
    IsTrue
    0.45
    PartResult
    0.45
    Brain
    0.44
     Slowly
    0.44
    oys
    0.44
    POSITIVE LOGITS
    着
    0.50
     administrativos
    0.48
     €,
    0.46
     afiliados
    0.45
     $,
    0.44
    向き
    0.44
     financeiros
    0.43
     releg
    0.43
     consag
    0.43
     montant
    0.42
    Activations Density 0.000%

    No Known Activations