© 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. 203931
    Prev
    Next
    INDEX
    Explanations

    events, locations, or descriptions

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

    characters, historical entities, and technical concepts

    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
     ETFs
    0.52
     Pitch
    0.50
     macromolecules
    0.49
     ET
    0.49
    <unused60>
    0.48
    MCs
    0.47
     biopsies
    0.46
     cleats
    0.45
     Fluids
    0.45
    u
    0.44
    POSITIVE LOGITS
     સી
    0.54
    ંત્ર
    0.53
     нале
    0.53
    𝒍
    0.52
     нама
    0.51
    린
    0.51
     उतर
    0.49
    ске
    0.48
     королев
    0.48
    𝒈
    0.48
    Activations Density 0.000%

    No Known Activations