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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12123
    Prev
    Next
    INDEX
    Explanations

    named entities and conjunctions

    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
    ureusement
    -0.99
    人が
    -0.96
     tapas
    -0.96
    Após
    -0.96
    пуска
    -0.96
    INESS
    -0.95
    чках
    -0.95
    Outras
    -0.95
     شهرد
    -0.94
     fairing
    -0.94
    POSITIVE LOGITS
     and
    1.31
     own
    1.26
     a
    1.24
    の人生
    1.10
     our
    1.08
     your
    0.99
    یره
    0.96
    埂
    0.96
    intera
    0.96
     his
    0.95
    Activations Density 0.035%

    No Known Activations