© 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. 59795
    Prev
    Next
    INDEX
    Explanations

    Men and words starting with Men

    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
     Hinblick
    -2.59
    一样的
    -2.50
     Acuerdo
    -2.44
    雳
    -2.42
    requipa
    -2.36
    issipp
    -2.31
    先は
    -2.28
    䊏
    -2.25
    <bos>
    -2.23
     utilizadas
    -2.20
    POSITIVE LOGITS
    0
    2.56
    1
    2.56
    2
    2.52
     Ако
    2.50
    鶺
    2.27
     The
    2.08
    a
    2.06
     tasteful
    1.99
     ghastly
    1.97
    Tetapi
    1.96
    Activations Density 0.010%

    No Known Activations