© 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. 113657
    Prev
    Next
    INDEX
    Explanations

    having trouble with

    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
    ]
    -1.97
     Why
    -1.80
     A
    -1.80
    ’
    -1.72
     multitude
    -1.70
     still
    -1.68
     
    -1.67
     plethora
    -1.63
     Who
    -1.63
     time
    -1.63
    POSITIVE LOGITS
    侂
    1.79
    ücks
    1.69
    Ԇ
    1.67
    Betyg
    1.59
    퐹
    1.59
    ър
    1.57
     ハーフ
    1.57
    盉
    1.56
    ÑO
    1.55
    ússia
    1.55
    Activations Density 0.017%

    No Known Activations