© 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. 31-GEMMASCOPE-2-RES-262K
    7. 127774
    Prev
    Next
    INDEX
    Explanations

    injuries, date, raise, companies, json

    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_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
     místo
    0.49
     producteurs
    0.45
    م
    0.45
     ಜನರು
    0.44
     luoghi
    0.44
     essentiels
    0.44
     essentiel
    0.44
     berguna
    0.43
     uomini
    0.43
     enseignants
    0.43
    POSITIVE LOGITS
     турни
    0.47
     lubricating
    0.43
     повы
    0.43
    Xa
    0.43
     Ony
    0.42
    ⏭
    0.42
     Lease
    0.40
     Client
    0.40
     Audiodate
    0.40
    Madam
    0.40
    Activations Density 0.010%

    No Known Activations