© 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. 61748
    Prev
    Next
    INDEX
    Explanations

    deputy followed by role

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

    dep

    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
     I
    0.54
    או
    0.54
     Mercedes
    0.53
     Mitsubishi
    0.53
     McAfee
    0.53
     P
    0.52
     carriera
    0.51
     Jó
    0.50
     घूमने
    0.50
    ώ
    0.50
    POSITIVE LOGITS
    Dep
    1.22
     Dep
    1.09
    dep
    1.03
     dep
    0.93
    depos
    0.88
    Depos
    0.88
    deposition
    0.87
     depositors
    0.86
     deposition
    0.84
     Deposits
    0.82
    Activations Density 0.026%

    No Known Activations