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. 7852
    Prev
    Next
    INDEX
    Explanations

    parenting and communication

    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
    јани
    -1.20
    ־ה
    -1.17
    ּוֹ
    -1.16
    садка
    -1.05
    ÑOS
    -1.05
    Vastaa
    -1.02
    וֹ
    -1.01
    zielle
    -1.00
     люди
    -1.00
     fishes
    -1.00
    POSITIVE LOGITS
     their
    2.09
     they
    1.48
    Their
    1.44
     habitat
    1.20
     foraging
    1.17
     territories
    1.15
     Their
    1.13
    their
    1.12
     females
    1.08
     thier
    1.08
    Activations Density 0.053%

    No Known Activations