© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72485
    Prev
    Next
    INDEX
    Explanations

    time periods relative to an event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     meja
    -1.68
    ：　
    -1.65
     bendera
    -1.64
     indígena
    -1.64
    の場合は
    -1.60
    ཽ
    -1.58
    좇
    -1.57
     munka
    -1.55
     mangel
    -1.55
    ейчас
    -1.53
    POSITIVE LOGITS
     that
    1.98
     —
    1.94
     you
    1.81
     they
    1.80
    l
    1.73
     I
    1.66
    f
    1.61
     The
    1.59
    r
    1.48
     nadzie
    1.46
    Activations Density 0.025%

    No Known Activations