© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3843
    Prev
    Next
    INDEX
    Explanations

    complex debugging scenarios, reputation, kit, client

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     заги
    1.23
     üçüncü
    1.08
     stupid
    1.07
     nameless
    1.00
    ノ
    0.99
    acağım
    0.99
     memorize
    0.98
     CONST
    0.98
    骷
    0.96
    кож
    0.96
    POSITIVE LOGITS
    prosperity
    1.28
     prosperity
    1.26
     emergence
    1.23
    Offers
    1.23
    Opportunities
    1.19
     vitality
    1.17
     flourishing
    1.17
     lifestyles
    1.16
     offers
    1.16
     utopian
    1.15
    Activations Density 0.132%

    No Known Activations