© 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. 178988
    Prev
    Next
    INDEX
    Explanations

    financial and administrative services

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

    repeatedly checks loop

    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
     nonexistent
    0.47
     чо
    0.45
     gaz
    0.45
    сет
    0.45
    años
    0.45
    EC
    0.44
    ()+
    0.44
    SAME
    0.44
    IMO
    0.44
    QE
    0.44
    POSITIVE LOGITS
    ႂ
    0.54
    irii
    0.45
     Away
    0.44
     Governing
    0.44
     Incorporation
    0.43
     Extending
    0.43
     Ngày
    0.41
     ascertaining
    0.41
     ƯCLN
    0.41
    ografi
    0.40
    Activations Density 0.001%

    No Known Activations