© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8090
    Prev
    Next
    INDEX
    Explanations

    and several

    np_acts-logits-general · gemini-2.5-flash-lite

    decimal point or end of number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    েন্দু
    0.44
    澧
    0.41
    ానిక
    0.41
    荩
    0.40
     বিষয়টা
    0.40
     titulares
    0.39
     চক্ষ
    0.39
    蛩
    0.39
    殓
    0.39
    了吗
    0.39
    POSITIVE LOGITS
    <eos>
    0.42
    don
    0.39
    z
    0.39
    pa
    0.39
    eg
    0.39
    p
    0.39
              
    0.38
    o
    0.38
    go
    0.38
    e
    0.38
    Activations Density 0.014%

    No Known Activations