© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 133722
    Prev
    Next
    INDEX
    Explanations

    Mt. Cook National Park, Spectra5, economical comb binding

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

    common health, metabolic panel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    legel
    0.50
    ]
    0.48
    लं
    0.48
     Batch
    0.47
    ཛ
    0.47
    ܟ
    0.47
     जय
    0.46
     dizi
    0.46
     Cabinet
    0.45
    )))
    0.45
    POSITIVE LOGITS
    的其他
    0.51
    у
    0.46
    的模型
    0.46
    的和
    0.45
    posto
    0.45
     empowered
    0.45
    ನ್
    0.44
    윽
    0.44
     તેમના
    0.44
    ‌,
    0.43
    Activations Density 0.001%

    No Known Activations