© 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. 175496
    Prev
    Next
    INDEX
    Explanations

    Kent Douglas Shaft

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

    backend, principles, sales, name, run, ViewModel

    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
    
    0.49
    üdis
    0.45
    、《
    0.45
     perpetuate
    0.43
    irts
    0.43
     מיט
    0.43
    <0x18>
    0.41
     millennials
    0.41
    ิ
    0.41
    .«
    0.41
    POSITIVE LOGITS
    Kent
    0.54
     Incl
    0.51
    tront
    0.51
     incl
    0.47
     Douglas
    0.46
     Kent
    0.46
     Shaft
    0.45
     Huey
    0.45
     Wound
    0.45
    incl
    0.43
    Activations Density 0.001%

    No Known Activations