© 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. 70383
    Prev
    Next
    INDEX
    Explanations

    mama and papa terms

    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
    </h3>
    -2.98
    '
    -2.69
    </strong>
    -2.59
     '
    -2.58
    ,'
    -2.47
    を使って
    -2.45
    panjang
    -2.45
     verbess
    -2.42
     sorgfäl
    -2.42
     is
    -2.38
    POSITIVE LOGITS
    a
    2.61
    However
    2.55
    Both
    2.45
    いれば
    2.33
    Perhaps
    2.28
    Most
    2.27
     pady
    2.25
    舳
    2.25
    Furthermore
    2.22
    These
    2.19
    Activations Density 0.002%

    No Known Activations