© 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. 16-GEMMASCOPE-2-RES-262K
    7. 3297
    Prev
    Next
    INDEX
    Explanations

    apple and its context

    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
    та
    1.55
    ق
    1.55
    т
    1.41
    લ
    1.30
    이었
    1.27
     powied
    1.27
     geométricas
    1.25
     вещества
    1.23
    的价格
    1.23
     académ
    1.21
    POSITIVE LOGITS
    -
    1.21
     by
    1.09
     Её
    1.00
    ’
    0.96
     Apple
    0.95
    Message
    0.91
    ↵
    0.89
    Version
    0.89
    는
    0.89
    Info
    0.88
    Activations Density 0.013%

    No Known Activations