© 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. 34-GEMMASCOPE-RES-131K
    4. 81760
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
     Jansen
    -0.85
    守り
    -0.74
     barre
    -0.74
     أمر
    -0.71
    sians
    -0.69
    zac
    -0.68
    sique
    -0.68
    endientes
    -0.68
    esian
    -0.66
    Behaviors
    -0.66
    POSITIVE LOGITS
    DoNot
    1.01
    DUMP
    0.87
    虚拟
    0.84
    𝒙
    0.83
     amenazas
    0.83
    phed
    0.82
     angef
    0.81
    xec
    0.80
     hacerlo
    0.80
     otras
    0.80
    Activations Density 0.006%

    No Known Activations