© 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. 10-GEMMASCOPE-RES-131K
    7. 44670
    Prev
    Next
    INDEX
    Explanations

    parenthetical explanations

    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_10/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
     
    -2.06
    猛地
    -1.72
    >
    -1.69
    ∽
    -1.63
     одним
    -1.58
    
    -1.58
    ка
    -1.55
     menyen
    -1.52
     одной
    -1.51
     selam
    -1.50
    POSITIVE LOGITS
    唬
    1.89
    神
    1.84
     them
    1.84
    pertino
    1.81
     Они
    1.80
    쨩
    1.78
     themselves
    1.77
    をします
    1.77
    تهى
    1.75
    遹
    1.75
    Activations Density 0.012%

    No Known Activations