© 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. 27994
    Prev
    Next
    INDEX
    Explanations

    colors and greetings

    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
     guérison
    0.43
     தொடர்பாக
    0.42
    ("/",
    0.42
    ότητας
    0.40
     with
    0.39
     ঘণ্টায়
    0.38
    שית
    0.38
    |_{\
    0.37
     dogged
    0.37
    ofType
    0.37
    POSITIVE LOGITS
     Hello
    0.42
     hello
    0.42
    Hello
    0.40
     هلا
    0.40
     Hallo
    0.39
     c
    0.39
    ellow
    0.39
    ú
    0.39
     اهلا
    0.39
     СА
    0.39
    Activations Density 0.024%

    No Known Activations