© 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. 39690
    Prev
    Next
    INDEX
    Explanations

    `Vi`, `b`, `df`, `ENV`, `ok`, `err`

    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
    ⎔
    -1.50
    鶿
    -1.41
     kleiner
    -1.40
    previously
    -1.38
    particularly
    -1.38
    despite
    -1.37
     Supplements
    -1.33
     enoj
    -1.31
    ですが
    -1.30
    Possui
    -1.30
    POSITIVE LOGITS
     in
    1.59
     undeniably
    1.44
     without
    1.41
    の詳細
    1.40
     дисци
    1.35
     on
    1.27
     noticeable
    1.27
     one
    1.26
    んですよね
    1.22
    طلاق
    1.22
    Activations Density 0.004%

    No Known Activations