© 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. 10-GEMMASCOPE-RES-131K
    7. 48485
    Prev
    Next
    INDEX
    Explanations

    names ending with "rick", "ng", "db", "ian", "well", "mas", "ny", "man", "oo", "ve", "P"

    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
     and
    -3.41
     from
    -3.14
     as
    -3.02
     now
    -2.55
     before
    -2.44
     strangely
    -2.27
     until
    -2.23
     relatively
    -2.23
     in
    -2.17
     first
    -2.14
    POSITIVE LOGITS
     verhind
    2.59
    粜
    2.52
     raiſ
    2.11
     corrom
    2.05
     😁
    2.02
    Välisling
    2.02
    鳚
    1.98
    横に
    1.98
     Dinas
    1.97
     pérd
    1.94
    Activations Density 0.072%

    No Known Activations