© 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. 16418
    Prev
    Next
    INDEX
    Explanations

    multi-lingual connectors

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

    conjunctions and if

    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
     يُ
    0.54
     تُ
    0.53
    .”
    0.51
     весьма
    0.50
     tzw
    0.50
     нередко
    0.50
     तकरीबन
    0.49
     äußerst
    0.49
     مُ
    0.46
     굉장
    0.46
    POSITIVE LOGITS
    和
    0.61
    如果
    0.59
     पनि
    0.57
     और
    0.54
    或者
    0.54
    删除
    0.53
     અને
    0.52
     आणि
    0.51
    的的
    0.51
    ដែល
    0.50
    Activations Density 0.005%

    No Known Activations