© 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-65K
    7. 50945
    Prev
    Next
    INDEX
    Explanations

    deer and antlers

    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_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
     chickens
    0.65
     poultry
    0.64
     chicken
    0.62
    猫
    0.59
     cats
    0.58
     Poultry
    0.57
     rept
    0.57
     cat
    0.56
    🐷
    0.56
     parrot
    0.55
    POSITIVE LOGITS
     antlers
    1.43
     antler
    1.29
    🦌
    1.19
     deer
    1.13
     elk
    1.11
    Deer
    1.11
    鹿
    1.11
     Deer
    1.08
     Elk
    1.00
     moose
    0.98
    Activations Density 0.032%

    No Known Activations