© 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. 10994
    Prev
    Next
    INDEX
    Explanations

    names and titles followed by specific words

    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
     individuellen
    -2.69
    ፨
    -2.66
     Erweiterung
    -2.63
     notwendigen
    -2.58
    靂
    -2.53
    芗
    -2.53
     uncover
    -2.50
     Aufführung
    -2.47
     Voraussetzung
    -2.45
    Ꭸ
    -2.45
    POSITIVE LOGITS
    '
    4.31
    {
    4.09
    ON
    2.80
    ER
    2.47
    ll
    2.36
    赑
    2.36
    AN
    2.34
    了很多
    2.33
     стоковые
    2.31
    ni
    2.22
    Activations Density 0.076%

    No Known Activations