© 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. 118513
    Prev
    Next
    INDEX
    Explanations

    names of people and organizations

    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
    <blockquote>
    -1.27
     править
    -1.14
     not
    -1.12
     several
    -1.12
     those
    -1.08
     went
    -1.08
     kaban
    -1.05
     some
    -1.04
     just
    -1.03
     despite
    -1.02
    POSITIVE LOGITS
    AfterViewInit
    1.16
     quintessential
    1.15
     idiotic
    1.12
    (=
    1.11
     .........
    1.05
    也可以
    1.03
     unbelievably
    1.02
     desear
    1.02
     astounding
    1.02
    either
    1.02
    Activations Density 0.372%

    No Known Activations