© 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. 109117
    Prev
    Next
    INDEX
    Explanations

    personal meeting

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

    administration, landlord, specific details

    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
    ujemy
    0.53
    ovar
    0.46
    ioners
    0.44
    umbria
    0.43
    oport
    0.43
    iero
    0.42
    roj
    0.42
    
    0.41
    ivid
    0.41
    AYA
    0.41
    POSITIVE LOGITS
     asset
    0.45
     oposición
    0.45
    ्व
    0.44
     ثابت
    0.43
     traction
    0.43
     첨
    0.43
    مدة
    0.42
     설치
    0.41
    ).*
    0.41
    Emphasis
    0.41
    Activations Density 0.000%

    No Known Activations