© 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. 5907
    Prev
    Next
    INDEX
    Explanations

    recent addition

    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
    നില്‍
    0.66
    െന്നാണ്
    0.65
     होकर
    0.62
    ιά
    0.59
    晦
    0.58
     freepik
    0.58
     minimizes
    0.56
    恪
    0.56
     শাসন
    0.55
    œuvre
    0.55
    POSITIVE LOGITS
     addition
    4.53
     adding
    4.34
     additions
    4.22
     added
    4.19
     add
    4.15
     Adding
    4.14
    添加
    4.07
    Adding
    4.07
     Addition
    4.07
     添加
    3.93
    Activations Density 1.015%

    No Known Activations