© 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. 235949
    Prev
    Next
    INDEX
    Explanations

    social or supply chain

    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
    ts
    0.54
     attorney
    0.49
    tle
    0.47
    awi
    0.46
    렸
    0.44
    ays
    0.44
    rti
    0.44
    mg
    0.43
    ospitals
    0.43
    ,"%
    0.43
    POSITIVE LOGITS
     există
    0.44
     Godzilla
    0.43
     Wikiped
    0.43
     നെറ്റ്‌വർ
    0.42
     Bronco
    0.42
     permitan
    0.42
     läng
    0.41
     techn
    0.40
     daripada
    0.40
     technologie
    0.40
    Activations Density 0.002%

    No Known Activations