© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82603
    Prev
    Next
    INDEX
    Explanations

    superscripts and subscripts

    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_34/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
    spelling
    -0.77
     пато
    -0.74
    olás
    -0.71
     dietro
    -0.69
    >\<
    -0.69
    iented
    -0.69
     Haines
    -0.67
    cane
    -0.66
    ティング
    -0.65
     شعب
    -0.65
    POSITIVE LOGITS
     subscript
    4.16
     subs
    4.09
     supers
    3.48
    supers
    2.69
     Supers
    2.63
    Supers
    2.59
    subs
    2.05
    Subs
    1.98
     indices
    1.98
     Subs
    1.93
    Activations Density 0.086%

    No Known Activations