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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11927
    Prev
    Next
    INDEX
    Explanations

    signed by teams

    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
    madeus
    -1.08
     piring
    -1.07
     errone
    -1.05
     UMKM
    -1.02
     residencial
    -1.01
     शीर्ष
    -1.01
    utrients
    -1.00
     primas
    -1.00
     hins
    -1.00
    UMENTO
    -0.98
    POSITIVE LOGITS
    uppo
    1.31
     arī
    1.25
    пів
    1.22
     Emergency
    1.18
    тивна
    1.10
     آید
    1.07
    絝
    1.05
     Department
    1.05
    стройство
    1.05
     kompati
    1.02
    Activations Density 0.082%

    No Known Activations