© 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. 65317
    Prev
    Next
    INDEX
    Explanations

    studded followed by c

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

    Absolutely, you are right

    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
     Gateway
    0.44
     patiently
    0.42
    博物馆
    0.42
     word
    0.41
     路
    0.41
     otherworldly
    0.41
    ്രി
    0.40
     pilgrimage
    0.39
     cocoon
    0.39
     Word
    0.39
    POSITIVE LOGITS
     정도
    0.54
     trộn
    0.51
    kraft
    0.49
    고
    0.48
     जाना
    0.46
     こんな
    0.45
     gekennzeichnet
    0.44
     বলল
    0.42
    㕩
    0.42
    nvim
    0.42
    Activations Density 0.000%

    No Known Activations