© 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. 90484
    Prev
    Next
    INDEX
    Explanations

    functional, properties, introduction, collections

    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
    以便
    -0.86
    gnus
    -0.82
     Вот
    -0.78
    kerk
    -0.75
    hint
    -0.75
     begitu
    -0.74
     slender
    -0.73
    uito
    -0.73
    skill
    -0.73
    NO
    -0.71
    POSITIVE LOGITS
    !***
    0.84
     besluit
    0.82
     quyết
    0.81
     Karya
    0.79
     kanal
    0.79
     ferait
    0.79
     CONDUIT
    0.78
     تصمیم
    0.77
    ştır
    0.75
    yness
    0.75
    Activations Density 0.000%

    No Known Activations