© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103510
    Prev
    Next
    INDEX
    Explanations

    fall, falls, fallen

    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
     to
    -1.62
     of
    -1.50
    )$
    -1.38
    lo
    -1.30
     oficjal
    -1.28
    ⤥
    -1.27
    š
    -1.27
    ta
    -1.24
     свобо
    -1.22
     كان
    -1.20
    POSITIVE LOGITS
     ältere
    1.63
    　　“
    1.53
    いかがでしたか
    1.41
    日记
    1.36
     spezielle
    1.24
    regated
    1.24
    ónico
    1.20
     isolé
    1.18
    上了
    1.18
    ers
    1.18
    Activations Density 0.021%

    No Known Activations