© 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. 93335
    Prev
    Next
    INDEX
    Explanations

    code snippets and punctuation

    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
    7
    -1.39
    8
    -1.38
    6
    -1.37
    5
    -1.34
    3
    -1.33
    2
    -1.32
    9
    -1.27
    4
    -1.22
     is
    -1.20
     alcune
    -1.15
    POSITIVE LOGITS
     our
    1.55
     nélk
    1.46
     érz
    1.31
     szív
    1.27
     kérd
    1.27
    éfonos
    1.27
     baterie
    1.26
    Недо
    1.26
    bezpiecz
    1.23
    xvii
    1.23
    Activations Density 0.037%

    No Known Activations