© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 16152
    Prev
    Next
    INDEX
    Explanations

    US states

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

    referring to sections by number

    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_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
     চতুর্থ
    0.38
    v
    0.38
    u
    0.38
     चतुर्थ
    0.37
    findIndex
    0.36
    in
    0.36
    asign
    0.36
     ৪র্থ
    0.36
    euler
    0.36
    op
    0.35
    POSITIVE LOGITS
     of
    0.41
     kasut
    0.39
    Η
    0.36
     τα
    0.36
     aprovechar
    0.35
     понять
    0.35
     opravdu
    0.35
     dejado
    0.35
    Stri
    0.35
     ingat
    0.34
    Activations Density 0.116%

    No Known Activations