© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 180
    Prev
    Next
    INDEX
    Explanations

    months of the year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_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
     commutative
    0.64
    뢰
    0.56
     idempot
    0.55
    modium
    0.52
     discern
    0.52
     strop
    0.52
     الوح
    0.51
     sire
    0.51
    ཱ
    0.51
     tink
    0.50
    POSITIVE LOGITS
     October
    3.94
     November
    3.88
     February
    3.86
     September
    3.81
     April
    3.80
     July
    3.76
     January
    3.75
     December
    3.70
     August
    3.66
     June
    3.64
    Activations Density 1.507%

    No Known Activations