© 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. 73403
    Prev
    Next
    INDEX
    Explanations

    classic examples and stories

    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
     actualmente
    -1.34
     trzy
    -1.25
     dlaczego
    -1.24
     специально
    -1.23
     betrifft
    -1.23
     ponieważ
    -1.22
    的主要
    -1.20
    のことを
    -1.20
     actuales
    -1.20
     generalmente
    -1.20
    POSITIVE LOGITS
     classic
    1.78
     classics
    1.42
    Shortly
    1.41
     classico
    1.33
     iconic
    1.30
     klasik
    1.30
     soupe
    1.30
    classic
    1.25
     of
    1.25
     absolue
    1.24
    Activations Density 0.049%

    No Known Activations