© 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. 48700
    Prev
    Next
    INDEX
    Explanations

    material properties and qualities

    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
     sweaty
    0.46
     ragion
    0.45
     demás
    0.41
    \%)
    0.40
     myster
    0.40
     aggrieved
    0.40
     hashedPassword
    0.40
    쿵
    0.40
     bosom
    0.40
     newspap
    0.40
    POSITIVE LOGITS
    XS
    0.47
    0.45
     removable
    0.38
    atán
    0.38
     ≥
    0.38
     reutil
    0.38
    Longrightarrow
    0.37
    ukset
    0.37
     acessórios
    0.37
    ik
    0.35
    Activations Density 0.010%

    No Known Activations