© 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. 40-GEMMASCOPE-2-RES-65K
    7. 338
    Prev
    Next
    INDEX
    Explanations

    apology, organized, interrupting, predictable

    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_40_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
    қ
    0.47
     etern
    0.43
    िक्ष
    0.43
     izgled
    0.43
     intimidated
    0.42
    ė
    0.42
    𝐝
    0.42
    <
    0.41
     uts
    0.41
    quele
    0.40
    POSITIVE LOGITS
    aktur
    0.48
     Signore
    0.42
     azure
    0.41
    luor
    0.39
     Jerusalem
    0.39
     餐
    0.39
     Antibodies
    0.38
     Sabemos
    0.38
    佛
    0.38
     শ্রীযুক্ত
    0.38
    Activations Density 0.004%

    No Known Activations