© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2308
    Prev
    Next
    INDEX
    Explanations

    people categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_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
     cea
    1.41
    It
    1.40
     acte
    1.38
     धमाल
    1.38
    それは
    1.34
     posao
    1.33
    elijk
    1.32
    l
    1.32
    তাহ
    1.32
    it
    1.27
    POSITIVE LOGITS
     infants
    1.96
     людей
    1.92
     pedestrians
    1.81
     dependents
    1.78
     retirees
    1.77
     individuals
    1.76
     patients
    1.75
     взрослых
    1.74
     victimes
    1.72
     victims
    1.71
    Activations Density 0.615%

    No Known Activations