© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59311
    Prev
    Next
    INDEX
    Explanations

    the more, the greater

    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
    really
    -1.27
    still
    -1.13
    perhaps
    -1.11
    hetically
    -1.09
    besides
    -1.08
    quite
    -1.08
    maybe
    -1.08
    exactly
    -1.05
    possibly
    -1.05
     wirklich
    -1.05
    POSITIVE LOGITS
     you
    1.59
     they
    1.52
     becomes
    1.42
     we
    1.40
     the
    1.34
     gets
    1.20
     become
    1.05
     înainte
    1.05
    越大
    1.02
     càng
    1.02
    Activations Density 0.013%

    No Known Activations