© 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. 31613
    Prev
    Next
    INDEX
    Explanations

    services and consultancy

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

    Block Paving

    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
     cilantro
    0.66
     パンツ
    0.66
    不一樣
    0.65
     Guerrero
    0.62
    airplane
    0.61
    搖
    0.61
    黴
    0.61
    اتھن
    0.60
     staffers
    0.59
    癒
    0.59
    POSITIVE LOGITS
     bespoke
    1.05
     postcode
    1.02
     adverts
    0.94
     UK
    0.89
     Consultancy
    0.88
     unrivalled
    0.86
     Maths
    0.86
     specialises
    0.84
     motorway
    0.84
     underpin
    0.82
    Activations Density 0.478%

    No Known Activations