© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13596
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    scan ips range vulnerabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     politič
    0.54
    کل
    0.52
    לות
    0.51
    বর্ষ
    0.50
     régime
    0.50
    න
    0.48
     diplomatic
    0.48
    liberal
    0.48
    ᇁ
    0.48
     nước
    0.48
    POSITIVE LOGITS
    1
    0.50
    s
    0.49
     Rats
    0.47
     pu
    0.45
     using
    0.45
    (
    0.44
     Staub
    0.43
     terminated
    0.43
     utilizzando
    0.43
     Micros
    0.43
    Activations Density 0.004%

    No Known Activations