© 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. 31-GEMMASCOPE-2-RES-65K
    7. 57010
    Prev
    Next
    INDEX
    Explanations

    using function objects

    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_65k_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
     Netz
    0.36
     ],
    0.35
     Kü
    0.34
    äl
    0.34
     ].
    0.33
    lç
    0.31
     allerlei
    0.31
     […]
    0.31
    ategor
    0.31
     ("[
    0.31
    POSITIVE LOGITS
    ᾗ
    0.35
     συνέχεια
    0.31
    လည်း
    0.31
     वर्मा
    0.31
    ก็ตาม
    0.30
     accompanying
    0.29
    ສາ
    0.29
    శ్
    0.29
    ણે
    0.29
     সরিয়ে
    0.29
    Activations Density 0.358%

    No Known Activations