© 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. 31-GEMMASCOPE-2-RES-262K
    4. 11725
    Prev
    Next
    INDEX
    Explanations

    abbreviations and company names

    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_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
     పూర్
    0.40
    ogén
    0.38
     божомолдору
    0.36
    stepToken
    0.36
    న్‌లో
    0.36
    桡
    0.36
    গঞ্জে
    0.35
     katva
    0.35
    ungkinkan
    0.35
    uesthouse
    0.35
    POSITIVE LOGITS
    株式会社
    0.38
     menacing
    0.35
     chaotic
    0.34
    ﭥ
    0.33
     avec
    0.32
     type
    0.32
    ಾನ
    0.32
     Constantinople
    0.32
    。
    0.32
     tipo
    0.31
    Activations Density 0.025%

    No Known Activations