© 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. 201615
    Prev
    Next
    INDEX
    Explanations

    Wikipedia article references

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

    English

    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
    ल्
    0.49
    错了
    0.47
    挑战
    0.46
    લ્
    0.43
    setCellValue
    0.43
    숩
    0.43
    ifizierung
    0.43
    setFooter
    0.43
    藓
    0.43
    Methylsulfanyl
    0.42
    POSITIVE LOGITS
     ari
    0.50
     انگلیسی
    0.49
     انگری
    0.47
     D
    0.47
     em
    0.45
     angla
    0.45
     sumber
    0.44
     anglais
    0.44
     で
    0.43
     Kont
    0.42
    Activations Density 0.000%

    No Known Activations