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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 1302
    Prev
    Next
    INDEX
    Explanations

    generative AI projects

    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
    0.52
    𝟬
    0.47
    KX
    0.46
    平均
    0.46
    0
    0.46
    管理
    0.46
    ຂອງ
    0.46
    丁
    0.45
    代
    0.45
    邝
    0.45
    POSITIVE LOGITS
     roto
    0.47
     RSC
    0.46
     digest
    0.46
     unidirectional
    0.46
     me
    0.45
     keel
    0.45
     termini
    0.45
     rewind
    0.44
     RSV
    0.44
     filo
    0.44
    Activations Density 0.000%

    No Known Activations