© 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-65K
    7. 65086
    Prev
    Next
    INDEX
    Explanations

    terms like age, payments, cons, effects, presentations, benefits, combinations

    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_65k_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
    asă
    0.45
    adır
    0.44
    asys
    0.44
    หรือ
    0.44
    规范
    0.43
    <unused981>
    0.43
    沃尔
    0.43
    皁
    0.42
    และ
    0.42
    ે
    0.42
    POSITIVE LOGITS
     subtypes
    0.52
     proteins
    0.51
     kinases
    0.49
     versions
    0.48
     genomes
    0.48
     responses
    0.46
     platelets
    0.46
     models
    0.46
     larvae
    0.46
     plated
    0.45
    Activations Density 0.002%

    No Known Activations