© 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. 34-GEMMASCOPE-RES-131K
    7. 93493
    Prev
    Next
    INDEX
    Explanations

    actions alongside or against

    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_34/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
    Plus
    -0.94
     Plus
    -0.90
     plus
    -0.86
    กัน
    -0.80
    plus
    -0.79
     Maha
    -0.79
    uchi
    -0.77
    жай
    -0.77
    在这里
    -0.76
     martes
    -0.75
    POSITIVE LOGITS
     alongside
    6.63
    Alongside
    4.44
     Alongside
    4.25
     beside
    3.38
     junto
    3.34
     کنار
    2.56
     accanto
    2.55
     fianco
    2.52
     côtés
    2.36
     side
    2.34
    Activations Density 0.114%

    No Known Activations