© 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. 72492
    Prev
    Next
    INDEX
    Explanations

    sequence numbers or indices

    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
     types
    -1.02
     gelukkig
    -0.96
     Schauspielerin
    -0.91
     Aquí
    -0.90
     nadal
    -0.88
     polska
    -0.88
    修炼
    -0.85
     length
    -0.85
     ответы
    -0.84
    に行って
    -0.84
    POSITIVE LOGITS
    ствовали
    1.01
     nifty
    0.98
    ínico
    0.98
     meninos
    0.93
     Since
    0.93
    вости
    0.92
    mão
    0.92
     inmate
    0.91
    ennom
    0.91
    omir
    0.91
    Activations Density 0.002%

    No Known Activations