© 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. 145156
    Prev
    Next
    INDEX
    Explanations

    days, females, herpes, source

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

    proposed solution

    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
     acabou
    0.50
    微妙
    0.48
    пла
    0.47
    𝗸
    0.47
     acab
    0.46
     จัก
    0.46
     acabó
    0.45
     แต่
    0.45
    ﻝ
    0.45
    സ്റ്റ്
    0.44
    POSITIVE LOGITS
    otin
    0.49
    icles
    0.48
     I
    0.47
     Bung
    0.46
    nsan
    0.44
     Macs
    0.43
     condiments
    0.43
     exporting
    0.42
     Exports
    0.42
     Hg
    0.42
    Activations Density 0.000%

    No Known Activations