© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 3675
    Prev
    Next
    INDEX
    Explanations

    I voted to

    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
     adequado
    -1.42
     aberto
    -1.33
     coeff
    -1.31
     czeko
    -1.30
     ワイン
    -1.29
    ﻄ
    -1.27
     förslag
    -1.26
    ydı
    -1.26
    ächtige
    -1.24
    движи
    -1.23
    POSITIVE LOGITS
     those
    1.65
     their
    1.61
     now
    1.55
     When
    1.27
     own
    1.26
     like
    1.26
    mathrm
    1.25
    Those
    1.22
    When
    1.22
     but
    1.20
    Activations Density 0.202%

    No Known Activations