© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56076
    Prev
    Next
    INDEX
    Explanations

    fusing process, stabilizing, edge ruler

    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
    ômes
    -0.80
    ctile
    -0.77
    Yale
    -0.75
     cultured
    -0.73
    weekend
    -0.73
     QtCore
    -0.72
    –
    -0.72
    thom
    -0.71
    ンテージ
    -0.71
     Yale
    -0.71
    POSITIVE LOGITS
     fusible
    1.27
     stabilizer
    1.18
     Stiff
    0.87
     stabili
    0.85
     destabili
    0.82
     bast
    0.81
     stabil
    0.80
     stabilize
    0.79
     Stabilization
    0.77
    TTL
    0.75
    Activations Density 0.014%

    No Known Activations