© 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. 3739
    Prev
    Next
    INDEX
    Explanations

    dog breeds and training

    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
     disinvestment
    0.54
    whitespace
    0.51
     प्रीपेड
    0.50
    ဆိုင်
    0.50
     استخدام
    0.49
     democratization
    0.49
    🌉
    0.49
    🏛
    0.48
     единица
    0.48
     monetization
    0.47
    POSITIVE LOGITS
     breed
    1.33
     dogs
    1.32
     dog
    1.13
     canine
    1.13
     breeds
    1.10
    犬
    1.06
     собак
    1.05
     bred
    1.04
     puppies
    1.04
    Dogs
    1.04
    Activations Density 0.198%

    No Known Activations