© 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-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 3578
    Prev
    Next
    INDEX
    Explanations

    semi- and semantically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_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
    регистри
    0.39
    衆
    0.38
    ствие
    0.37
    ствия
    0.36
     shove
    0.36
     المل
    0.36
     SEEK
    0.35
    谄
    0.35
    ieving
    0.35
    PORTS
    0.35
    POSITIVE LOGITS
     sem
    1.23
     semi
    1.23
     Semi
    1.14
    Semi
    1.11
     semic
    1.09
     semis
    1.08
     semia
    1.03
    semi
    1.02
     semif
    0.99
     Sem
    0.97
    Activations Density 0.012%

    No Known Activations