© 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. 10-GEMMASCOPE-RES-131K
    7. 84239
    Prev
    Next
    INDEX
    Explanations

    in turn, without any

    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
     этого
    -1.48
     that
    -1.38
     goe
    -1.37
     eisen
    -1.37
     этой
    -1.34
     maioria
    -1.32
     puits
    -1.30
    🟣
    -1.30
    はその
    -1.30
    står
    -1.30
    POSITIVE LOGITS
     while
    1.83
     despite
    1.55
     Could
    1.41
    مزید
    1.39
     Less
    1.37
     but
    1.36
     для
    1.31
    Did
    1.31
    了一句
    1.30
     ਨੂੰ
    1.30
    Activations Density 0.015%

    No Known Activations