© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 123348
    Prev
    Next
    INDEX
    Explanations

    stars per galaxy

    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
    "
    0.43
    Children
    0.41
    :
    0.41
    :"
    0.41
    H
    0.40
    WORTH
    0.40
    September
    0.40
    LE
    0.40
    Rot
    0.39
    ЛО
    0.39
    POSITIVE LOGITS
     возраст
    0.47
     учиты
    0.46
     পারেন
    0.45
     bodice
    0.45
    arily
    0.44
    が可能
    0.44
     शकतो
    0.44
     গোষ্ঠ
    0.43
     /\.
    0.42
     μπορούν
    0.42
    Activations Density 0.003%

    No Known Activations