© 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. 26380
    Prev
    Next
    INDEX
    Explanations

    sales director

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

    Copilot, sales pitches, internet knowledge

    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
    ﾙ
    0.50
    ان
    0.47
    拶
    0.47
    ப்பில்
    0.45
     whipping
    0.44
    expensive
    0.43
    blit
    0.43
    λ
    0.43
    லீ
    0.42
    hundred
    0.42
    POSITIVE LOGITS
     aquello
    0.54
     odio
    0.51
     lector
    0.50
     feitos
    0.50
     getir
    0.50
     x
    0.49
     Feria
    0.48
    isma
    0.47
     unis
    0.47
     cabello
    0.46
    Activations Density 0.000%

    No Known Activations