© 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. 34-GEMMASCOPE-RES-131K
    7. 111124
    Prev
    Next
    INDEX
    Explanations

    code functions or methods

    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_34/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
    ჻
    -1.55
    irée
    -1.47
    particularly
    -1.47
    llte
    -1.40
    っているので
    -1.35
     soooo
    -1.35
     opinião
    -1.34
     sooo
    -1.34
    ’;
    -1.32
     ainfi
    -1.32
    POSITIVE LOGITS
    ()
    4.50
    (){
    3.27
    ()
    3.08
     ()
    3.05
     (
    2.80
    ():
    2.66
    ())
    2.52
    (){
    2.33
    ();
    2.25
    >()
    2.14
    Activations Density 0.040%

    No Known Activations