© 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. 39817
    Prev
    Next
    INDEX
    Explanations

    building filters and operators

    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
    ~•
    -1.28
    kult
    -1.20
     尺寸
    -1.16
    ידות
    -1.16
    petits
    -1.13
    kenzo
    -1.12
    nhung
    -1.12
     confuso
    -1.09
    jerk
    -1.06
    pneu
    -1.06
    POSITIVE LOGITS
     filter
    1.21
    filter
    1.15
     you
    1.13
    𝚒
    1.07
     multiple
    1.03
    filters
    1.03
     zusätzlich
    1.01
     search
    1.01
     key
    1.00
    ofil
    0.99
    Activations Density 0.074%

    No Known Activations