© 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. 31-GEMMASCOPE-2-RES-65K
    7. 27206
    Prev
    Next
    INDEX
    Explanations

    applying their insights

    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_31_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
    ିକ
    0.53
    
    0.49
    鏻
    0.49
    akap
    0.48
    ılarak
    0.48
    кл
    0.48
    ALLOW
    0.46
    鈮
    0.46
    στι
    0.46
    KCl
    0.46
    POSITIVE LOGITS
    <0x0D>
    0.46
     parlament
    0.44
    orious
    0.43
    </strong>
    0.42
     bulan
    0.42
     de
    0.41
     esimerkiksi
    0.41
     asserts
    0.41
     Teor
    0.41
     Ouverture
    0.41
    Activations Density 0.026%

    No Known Activations