© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 120102
    Prev
    Next
    INDEX
    Explanations

    Analog Devices

    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
     ટે
    0.64
     पाण्या
    0.56
     puisque
    0.55
    httpRequest
    0.55
     برای
    0.54
     रा
    0.53
    سی
    0.52
    𝒔
    0.52
     अर्जित
    0.52
     somente
    0.52
    POSITIVE LOGITS
     ane
    0.50
     Brahman
    0.46
     all
    0.42
     highs
    0.42
     an
    0.42
    <?
    0.42
     coll
    0.41
     geändert
    0.41
     anni
    0.41
    仙
    0.40
    Activations Density 0.000%

    No Known Activations