© 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-65K
    7. 30388
    Prev
    Next
    INDEX
    Explanations

    global variables and callables

    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
     добавить
    0.50
     Ль
    0.49
     వచ్చిన
    0.49
    秵
    0.49
     jakiś
    0.48
     より
    0.45
     नष्ट
    0.45
     хуже
    0.45
     неред
    0.44
    
    0.44
    POSITIVE LOGITS
     callable
    0.49
     anticip
    0.41
     resuscitation
    0.39
     kpc
    0.39
     attractor
    0.39
     readiness
    0.38
     participa
    0.38
     covari
    0.37
     Readiness
    0.37
     caregiver
    0.36
    Activations Density 0.002%

    No Known Activations