© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 414
    Prev
    Next
    INDEX
    Explanations

    iPhones and in-store

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     मित्त
    0.31
    ២
    0.30
     murderous
    0.30
    ૩
    0.28
     अनुरोध
    0.27
    ཥ
    0.27
    ుడు
    0.26
     עבור
    0.26
     hommage
    0.26
    ༩
    0.26
    POSITIVE LOGITS
     and
    0.29
     or
    0.28
     reduces
    0.25
    <strong>
    0.24
     Medicaid
    0.24
     mainstream
    0.23
             
    0.23
     ER
    0.23
     promotes
    0.23
     Adolescent
    0.22
    Activations Density 1.705%

    No Known Activations