© 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. 60373
    Prev
    Next
    INDEX
    Explanations

    services and technology

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

    suspended account

    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
     Maths
    0.50
     a
    0.48
    晤
    0.48
     Wolves
    0.47
     J
    0.45
     Indicator
    0.45
     an
    0.43
     Close
    0.43
     idiots
    0.43
     Freem
    0.43
    POSITIVE LOGITS
    layered
    0.49
     organique
    0.47
     tecnologie
    0.47
     sprzedaży
    0.45
    sigh
    0.45
     servent
    0.44
    Fert
    0.43
     tecnologías
    0.42
    ຊີ
    0.42
    苼
    0.42
    Activations Density 0.002%

    No Known Activations