© 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. 102479
    Prev
    Next
    INDEX
    Explanations

    New Relic monitors

    np_acts-logits-general · gemini-2.5-flash-lite

    proper nouns referring to technology brands, products, and services.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     with
    -2.19
    There
    -1.82
     there
    -1.73
    With
    -1.53
     There
    -1.45
     With
    -1.44
     If
    -1.40
     Without
    -1.40
     making
    -1.36
     Those
    -1.34
    POSITIVE LOGITS
    鲥
    1.46
    躄
    1.38
    𓁹
    1.38
    鳚
    1.34
     bì
    1.34
    chers
    1.33
    垰
    1.33
    
    1.30
     conect
    1.28
    isait
    1.28
    Activations Density 0.236%

    No Known Activations