© 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. 66471
    Prev
    Next
    INDEX
    Explanations

    requirementsnecessityprerequisites

    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
    \
    -3.20
    )
    -3.20
    ."
    -3.02
    A
    -2.84
    O
    -2.67
    …
    -2.41
    ?”
    -2.34
     dismal
    -2.23
    {
    -2.22
    '
    -2.20
    POSITIVE LOGITS
    鰾
    3.14
    Donativos
    2.75
    勦
    2.70
    ญี่ป
    2.47
    ſelves
    2.44
    鄚
    2.33
    阇
    2.28
     transparencia
    2.28
    哢
    2.25
     assistir
    2.22
    Activations Density 0.052%

    No Known Activations