© 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. 40-GEMMASCOPE-2-RES-262K
    4. 195605
    Prev
    Next
    INDEX
    Explanations

    actions or transactions

    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_40_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
    erala
    0.41
    愆
    0.40
    టికి
    0.40
    లతో
    0.38
    orini
    0.38
    лады
    0.37
    াচার
    0.36
     suppresses
    0.36
    剷
    0.36
    Critic
    0.35
    POSITIVE LOGITS
     संक्षिप्त
    0.47
    Attachments
    0.45
     प्रस्तुत
    0.42
     Sets
    0.40
     Prel
    0.40
     दृढ़
    0.40
    附件
    0.39
     Bent
    0.39
    în
    0.39
    サスカ
    0.38
    Activations Density 0.001%

    No Known Activations