© 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-262K
    7. 18845
    Prev
    Next
    INDEX
    Explanations

    explaining with examples

    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_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
     Aunque
    0.72
    和其他
    0.72
     hopefully
    0.69
     although
    0.69
     special
    0.68
    쨌
    0.68
     olmak
    0.66
     customized
    0.66
    യ്യാ
    0.66
    並
    0.64
    POSITIVE LOGITS
    Consider
    2.35
     Consider
    2.29
     consider
    2.25
    Take
    1.94
    consider
    1.91
     Take
    1.74
    take
    1.71
     considere
    1.55
     take
    1.54
     considérons
    1.53
    Activations Density 0.163%

    No Known Activations