© 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. 122562
    Prev
    Next
    INDEX
    Explanations

    foreign language words and phrases

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

    Drum Machine

    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
    ه
    0.64
    a
    0.56
    ה
    0.50
     FileReader
    0.50
    导体
    0.48
     nya
    0.48
     Cairo
    0.48
    因為
    0.47
     Lx
    0.47
    文件
    0.47
    POSITIVE LOGITS
     разно
    0.50
     precisión
    0.49
     বছর
    0.47
     simplic
    0.47
    IgnoreCase
    0.46
    э
    0.45
     сам
    0.45
    indel
    0.45
    racht
    0.45
    lač
    0.44
    Activations Density 0.000%

    No Known Activations