© 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-262K
    7. 34846
    Prev
    Next
    INDEX
    Explanations

    Obsidian Order, Shadow stresses

    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
    敌人
    0.45
    צוני
    0.43
    ્
    0.43
    ୍
    0.43
    듈
    0.42
     экзем
    0.42
     श्रृ
    0.40
     configuring
    0.40
    மில்லை
    0.40
    ཱ
    0.40
    POSITIVE LOGITS
    بعض
    0.44
     বারবার
    0.39
     zahlreichen
    0.38
     cidade
    0.38
     nombreux
    0.37
     cidades
    0.37
     periód
    0.37
    ことがある
    0.37
    hover
    0.37
     कामों
    0.37
    Activations Density 0.014%

    No Known Activations