© 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. 39491
    Prev
    Next
    INDEX
    Explanations

    handle claims and legal matters

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

    legal and financial details

    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
    縣
    0.75
     federally
    0.66
    祕
    0.64
    美國
    0.64
    Colorado
    0.63
    廳
    0.63
    Texas
    0.62
     dollari
    0.62
    Ohio
    0.61
    汙
    0.61
    POSITIVE LOGITS
     timescale
    0.84
     enquiries
    0.80
     envisaged
    0.77
     underpinned
    0.77
     timescales
    0.72
     envis
    0.71
     carers
    0.70
     adverts
    0.69
     specialises
    0.68
     endeavoured
    0.67
    Activations Density 0.240%

    No Known Activations