© 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. 22-GEMMASCOPE-RES-131K
    7. 25953
    Prev
    Next
    INDEX
    Explanations

    Wisconsin, State

    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
    also
    -1.82
    ]
    -1.80
    _
    -1.79
    t
    -1.74
     ‘
    -1.64
     outras
    -1.60
    of
    -1.59
    on
    -1.56
     prazo
    -1.54
     –
    -1.53
    POSITIVE LOGITS
     has
    1.73
    وقتی
    1.68
    مدیر
    1.65
    荩
    1.63
    𝐎
    1.58
    Çok
    1.57
    、《
    1.56
    دکتر
    1.52
    ｢
    1.52
    ୌ
    1.52
    Activations Density 0.019%

    No Known Activations