© 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. 22-GEMMASCOPE-RES-131K
    7. 70990
    Prev
    Next
    INDEX
    Explanations

    file operation verbs

    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
     juſ
    -1.38
     bemerk
    -1.38
     作り方
    -1.38
    $};
    -1.34
    が必要です
    -1.34
    Datuak
    -1.33
     hongos
    -1.32
     passende
    -1.30
    vég
    -1.30
     dessinée
    -1.27
    POSITIVE LOGITS
    able
    1.64
    ers
    1.53
    d
    1.30
    -
    1.27
    with
    1.27
     techniques
    1.26
    了一個
    1.23
    1
    1.23
     as
    1.23
    y
    1.23
    Activations Density 0.039%

    No Known Activations