© 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. 10-GEMMASCOPE-RES-131K
    7. 104536
    Prev
    Next
    INDEX
    Explanations

    `PIP` mobility, `nucleic acid`

    np_acts-logits-general · gemini-2.5-flash-lite

    mathematical and programming symbols like "$", "PIP", and reference notations like column/row indicators in spreadsheets.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    en
    -4.34
    1
    -3.34
    i
    -3.30
    「
    -3.05
    (
    -2.84
    “
    -2.73
    5
    -2.66
    ...?
    -2.64
    ma
    -2.63
     flurry
    -2.61
    POSITIVE LOGITS
    鼍
    2.72
    🫅
    2.53
     観光
    2.50
    šiť
    2.41
     Hinsicht
    2.36
    gucig
    2.36
     nebst
    2.33
    込んだ
    2.28
     outras
    2.28
    ⾯
    2.25
    Activations Density 0.002%

    No Known Activations