© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 65021
    Prev
    Next
    INDEX
    Explanations

    total quantity

    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
    ⟣
    -1.63
     内衣
    -1.53
    𖣔
    -1.50
    ➃
    -1.46
    aceite
    -1.45
    esome
    -1.45
     短发
    -1.44
    moiselle
    -1.42
    legten
    -1.39
     ilust
    -1.38
    POSITIVE LOGITS
     all
    2.00
     any
    1.67
     of
    1.58
     new
    1.45
     모든
    1.41
     both
    1.40
     ALL
    1.34
     related
    1.33
     всех
    1.32
    的一切
    1.31
    Activations Density 0.040%

    No Known Activations