© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39990
    Prev
    Next
    INDEX
    Explanations

    proper nouns and company names

    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
     are
    -3.25
    S
    -2.56
    没什么
    -2.48
    ſelves
    -2.45
    糨
    -2.44
    on
    -2.36
     \
    -2.34
    u
    -2.34
    at
    -2.27
     he
    -2.27
    POSITIVE LOGITS
    What
    2.92
    Here
    2.73
    From
    2.59
    which
    2.53
    垕
    2.42
    When
    2.36
    After
    2.28
    蓴
    2.28
    梘
    2.27
    There
    2.22
    Activations Density 0.007%

    No Known Activations