© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 1238
    Prev
    Next
    INDEX
    Explanations

    parts of an entity

    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_22_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
     사례
    0.56
     ଏ
    0.56
    Concept
    0.55
    С
    0.53
     similaires
    0.53
    ص
    0.53
    époque
    0.53
     όπως
    0.53
    Α
    0.51
     konular
    0.51
    POSITIVE LOGITS
     entire
    0.78
     edges
    0.66
     underlying
    0.65
     resulting
    0.63
     gesamte
    0.59
     ensuing
    0.58
     innermost
    0.58
     walls
    0.56
     slightest
    0.56
     reactor
    0.56
    Activations Density 0.949%

    No Known Activations