© 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. 40-GEMMASCOPE-2-RES-262K
    7. 119349
    Prev
    Next
    INDEX
    Explanations

    linking options or consequences

    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_40_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
     увеличи
    0.39
     experimented
    0.39
     partenza
    0.38
     aumento
    0.38
     жаса
    0.37
     hypertro
    0.37
     조사
    0.37
    哣
    0.37
     출발
    0.36
     збіль
    0.36
    POSITIVE LOGITS
    èm
    0.43
    เซ
    0.41
     মর্ম
    0.39
     saver
    0.38
    சிக்க
    0.38
    સમ
    0.37
    വിൽ
    0.37
     ভবিষ্যতের
    0.37
    ברת
    0.36
    デア
    0.36
    Activations Density 0.005%

    No Known Activations