© 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. 40-GEMMASCOPE-2-RES-262K
    7. 93
    Prev
    Next
    INDEX
    Explanations

    programming code and classes

    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
     olmadığı
    0.43
     bouillon
    0.43
    Ⴊ
    0.40
    OTTOM
    0.38
     sulphate
    0.38
    瀰
    0.38
     sebum
    0.38
     vaiht
    0.38
     hommes
    0.37
     ⏮
    0.37
    POSITIVE LOGITS
     Base
    1.02
    Base
    0.99
     base
    0.87
    Abstract
    0.83
     Abstract
    0.82
    base
    0.82
     NSObject
    0.77
     BaseModel
    0.75
     MonoBehaviour
    0.75
     StatelessWidget
    0.73
    Activations Density 0.017%

    No Known Activations