© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 150219
    Prev
    Next
    INDEX
    Explanations

    also, too

    np_acts-logits-general · gemini-2.5-flash-lite

    also, and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     normalization
    0.44
    그
    0.44
    矯
    0.43
    提高
    0.43
    増加
    0.42
    依次
    0.42
    逼
    0.42
    格
    0.41
    舒
    0.41
     normalizing
    0.40
    POSITIVE LOGITS
     też
    0.61
     również
    0.55
     కూడా
    0.54
    လည်း
    0.54
     কথাও
    0.53
     també
    0.49
     भी
    0.48
     দুর্ঘটনা
    0.47
     également
    0.47
     ankaŭ
    0.47
    Activations Density 0.000%

    No Known Activations