© 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. 60270
    Prev
    Next
    INDEX
    Explanations

    month names in datelines

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

    dates with months

    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
     Ferm
    0.51
     Fecha
    0.47
     Sinne
    0.45
    ,
    0.43
    ന്റ
    0.43
     Massachusetts
    0.42
     Versions
    0.42
    ▪
    0.42
    𝘈
    0.42
    していた
    0.41
    POSITIVE LOGITS
     fintech
    0.55
     totalPrice
    0.45
     שלא
    0.45
     electorate
    0.44
    कांग्रेस
    0.44
     lawmaker
    0.42
     payments
    0.41
     lawmakers
    0.41
     billionaire
    0.40
     payouts
    0.40
    Activations Density 0.002%

    No Known Activations