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-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 499
    Prev
    Next
    INDEX
    Explanations

    engage in or with

    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_16_width_262k_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
    '
    1.19
    v
    1.02
    h
    0.99
    3
    0.98
    ా
    0.98
    ella
    0.93
    的
    0.91
    ves
    0.90
    coast
    0.90
    candidate
    0.89
    POSITIVE LOGITS
     bunches
    1.27
    ﺕ
    1.15
     vocalist
    1.10
    끔
    1.09
     sosok
    1.09
     заниматься
    1.04
     scont
    1.04
     pneus
    1.03
     profesora
    1.02
    να
    1.02
    Activations Density 0.023%

    No Known Activations