© 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. 139186
    Prev
    Next
    INDEX
    Explanations

    business industries and finance

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

    artists, studios, communication, basalt

    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
     erste
    0.48
     eerste
    0.45
     fundación
    0.44
     satisfacción
    0.43
     membr
    0.42
     chiede
    0.41
    َة
    0.41
    butyl
    0.41
     habite
    0.41
    rist
    0.41
    POSITIVE LOGITS
     Soren
    0.46
     बहू
    0.45
    🔢
    0.40
     shov
    0.39
     नंबर
    0.39
     Iron
    0.38
     descriptions
    0.38
     Shadows
    0.38
    🥃
    0.38
     "\(
    0.38
    Activations Density 0.001%

    No Known Activations