Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7822
    Prev
    Next
    INDEX
    Explanations

    copyright notices and licenses

    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
    ússia
    -0.88
     pietra
    -0.82
    ztus
    -0.82
     Inde
    -0.81
    прав
    -0.79
     fresco
    -0.79
    ündigung
    -0.79
    chtung
    -0.77
     khal
    -0.76
     nutri
    -0.76
    POSITIVE LOGITS
     then
    1.43
     então
    1.09
     Then
    1.09
    Then
    1.07
     entonces
    1.00
    zbęd
    0.90
     тогда
    0.90
    €”
    0.89
     THEN
    0.88
     than
    0.85
    Activations Density 0.004%

    No Known Activations