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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11407
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or symbols

    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_22/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
    Really
    -1.03
    OPTS
    -0.94
     renkli
    -0.91
    Certainly
    -0.91
    terness
    -0.91
     ekolog
    -0.90
    ResponseEntity
    -0.89
    },$
    -0.89
     sementes
    -0.89
    mapStateToProps
    -0.88
    POSITIVE LOGITS
     далее
    1.00
     further
    0.94
     another
    0.91
     any
    0.90
     qualquer
    0.88
     Maximal
    0.87
    回目の
    0.85
    PROVID
    0.85
     tarjo
    0.84
     добавля
    0.83
    Activations Density 0.003%

    No Known Activations