© 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. 8572
    Prev
    Next
    INDEX
    Explanations

    government administration and services

    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
    StoryboardSegue
    -1.45
    حتی
    -1.40
    țiuni
    -1.35
    نکته
    -1.33
    鰨
    -1.31
    sellors
    -1.30
    greifen
    -1.30
    берт
    -1.30
    ⇓
    -1.29
    튿
    -1.29
    POSITIVE LOGITS
     from
    1.60
     when
    1.53
     and
    1.48
     including
    1.34
     now
    1.32
     
    1.30
     government
    1.30
     Although
    1.27
     A
    1.26
     merely
    1.21
    Activations Density 0.081%

    No Known Activations