© 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. 34-GEMMASCOPE-RES-131K
    7. 6968
    Prev
    Next
    INDEX
    Explanations

    heroes saving action

    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_34/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
    dcterms
    -0.91
    έ
    -0.90
    ukov
    -0.89
     भारतीय
    -0.88
    тельству
    -0.84
     producing
    -0.83
     AssertionError
    -0.81
     replacement
    -0.81
    NewUrlParser
    -0.81
    ktır
    -0.80
    POSITIVE LOGITS
     fight
    2.11
     fighting
    2.11
     fights
    1.82
    fighting
    1.70
     saving
    1.68
     adventures
    1.57
     rescuing
    1.53
    fight
    1.52
     save
    1.52
     adventure
    1.51
    Activations Density 0.060%

    No Known Activations