© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129378
    Prev
    Next
    INDEX
    Explanations

    beginnings of phrases or clauses

    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
     сначала
    -1.13
     chré
    -1.08
     nuestro
    -1.08
     просто
    -1.07
     Example
    -1.05
     nuestra
    -1.04
     glaubt
    -1.02
    投手
    -1.02
     만들
    -1.00
     zunächst
    -0.98
    POSITIVE LOGITS
     pozo
    1.43
     funcionando
    1.33
    Depuis
    1.33
     alene
    1.32
     elétrico
    1.32
     digno
    1.31
     Propiedad
    1.30
     congreso
    1.27
     ilha
    1.26
    cised
    1.25
    Activations Density 0.015%

    No Known Activations