© 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. 31-GEMMASCOPE-2-RES-65K
    7. 10743
    Prev
    Next
    INDEX
    Explanations

    multi-language text components

    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_31_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
     nöt
    0.30
    ),
    0.27
     silicon
    0.27
     reinforcements
    0.27
     overlap
    0.26
     zusätzlich
    0.26
     rats
    0.25
    .
    0.25
    6
    0.25
     cancers
    0.25
    POSITIVE LOGITS
     Бүгенге
    0.34
     Несмотря
    0.32
     समाचार
    0.31
    㐄
    0.31
     阅读全文
    0.30
     നിരവധി
    0.30
     בשנת
    0.29
    <unused2040>
    0.29
    亠
    0.29
     некоторые
    0.29
    Activations Density 0.193%

    No Known Activations