© 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. 22-GEMMASCOPE-RES-131K
    4. 67508
    Prev
    Next
    INDEX
    Explanations

    current selection

    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
    reeg
    -1.00
     caneca
    -0.84
     originales
    -0.83
     оригина
    -0.82
    бата
    -0.82
    ープル
    -0.81
    insured
    -0.81
     créé
    -0.80
     WaitForSeconds
    -0.79
    once
    -0.78
    POSITIVE LOGITS
     current
    1.86
    current
    1.30
    当前
    1.28
     getCurrent
    1.28
     теку
    1.27
     currently
    1.25
     当前
    1.16
    mCurrent
    1.14
    Current
    1.13
     selected
    1.08
    Activations Density 0.055%

    No Known Activations