© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14381
    Prev
    Next
    INDEX
    Explanations

    family relationship terms

    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
     it
    -1.69
     this
    -1.34
     that
    -1.27
     geschikt
    -1.07
    "
    -1.06
     we
    -1.05
     does
    -1.03
    _
    -1.01
    ?
    -1.00
     when
    -0.98
    POSITIVE LOGITS
    푉
    1.33
    אח
    1.13
    ära
    1.08
    geladen
    1.05
    <<<<<<<<<<<<
    1.05
    งิน
    1.04
     グラフ
    1.04
    ፲
    1.04
     červená
    1.04
    kening
    1.03
    Activations Density 0.001%

    No Known Activations