© 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. 105598
    Prev
    Next
    INDEX
    Explanations

    names and specific entities

    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
     of
    -1.47
     everyone
    -1.45
     will
    -1.25
    也算
    -1.21
     even
    -1.21
     auténtico
    -1.20
    </h2>
    -1.20
     Entfer
    -1.17
     this
    -1.16
     these
    -1.15
    POSITIVE LOGITS
    "-"
    1.24
    ☑️
    1.23
     nigger
    1.13
     CTRL
    1.12
    🍂
    1.11
     การ
    1.11
    gradable
    1.09
    😯
    1.09
     eux
    1.09
    ByPrimaryKey
    1.08
    Activations Density 0.057%

    No Known Activations