© 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. 101100
    Prev
    Next
    INDEX
    Explanations

    package names and code indicators

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

    import declarations

    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
     Desenvolvimento
    0.50
     Recommended
    0.48
     Appointments
    0.47
     Recommendations
    0.46
    ᅦ
    0.46
     Academy
    0.46
     Developer
    0.46
     App
    0.46
     Started
    0.45
     Ρ
    0.45
    POSITIVE LOGITS
    years
    0.50
    roles
    0.48
    ending
    0.48
    ofi
    0.48
    negative
    0.47
    payers
    0.47
    infrared
    0.47
    shape
    0.47
    linestyle
    0.47
    và
    0.47
    Activations Density 0.001%

    No Known Activations