Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12257
    Prev
    Next
    INDEX
    Explanations

    __init__ method

    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_16k_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
     нужен
    0.55
     mikä
    0.54
     }:
    0.48
    ↵
    0.47
     declare
    0.46
     нужна
    0.46
     don
    0.46
     :");
    0.46
     =
    0.45
     braucht
    0.45
    POSITIVE LOGITS
    ב
    0.47
    memiş
    0.46
    ব
    0.44
    蝕
    0.44
    ίας
    0.42
    ceğ
    0.41
    ス
    0.41
    éticos
    0.40
    י
    0.40
    ۀ
    0.40
    Activations Density 0.027%

    No Known Activations