© 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. 30461
    Prev
    Next
    INDEX
    Explanations

    and address or your sector

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

    open the Run dialog

    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
    ટો
    0.51
    MaxIntensity
    0.49
    DBObject
    0.48
    㓡
    0.48
     ቦ
    0.47
     earthy
    0.46
     উত্তেজিত
    0.45
    奶油
    0.45
     effluents
    0.45
    新鲜
    0.44
    POSITIVE LOGITS
    いただく
    0.42
     Supervisors
    0.41
     Angkor
    0.40
     violating
    0.39
     Kā
    0.39
     seventeenth
    0.39
    ారు
    0.39
     Liberia
    0.38
    𝟙
    0.38
     tahun
    0.37
    Activations Density 0.000%

    No Known Activations