© 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. 22-GEMMASCOPE-RES-131K
    7. 93087
    Prev
    Next
    INDEX
    Explanations

    Gaze patterns, Black pine, Fate of

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

    statistical significance notations in scientific papers, particularly "p < 0.001" and similar values.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Which
    -1.15
     forbin
    -1.02
     registrados
    -1.01
     skry
    -1.00
     which
    -1.00
     kaca
    -0.99
    ˂
    -0.98
    pions
    -0.96
    }".
    -0.96
     søndag
    -0.96
    POSITIVE LOGITS
     inappro
    1.04
    Bibliografie
    1.02
    Legende
    1.02
     ovation
    0.99
     sinistra
    0.99
     lamentable
    0.98
     DDS
    0.98
    等的
    0.98
     meinem
    0.97
     Ctr
    0.96
    Activations Density 0.000%

    No Known Activations