© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2297
    Prev
    Next
    INDEX
    Explanations

    animal breeds and genetics

    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
     uczni
    0.44
    捃
    0.44
     Reuse
    0.42
     monotonically
    0.42
     кван
    0.42
     Device
    0.42
    WOM
    0.42
     LinkedIn
    0.41
    멱
    0.41
     контек
    0.41
    POSITIVE LOGITS
     breed
    1.68
     breeds
    1.47
     breeders
    1.44
     bred
    1.34
     breeder
    1.33
    breed
    1.33
     breeding
    1.31
    Breed
    1.26
     genetics
    1.25
     Breed
    1.20
    Activations Density 0.048%

    No Known Activations