© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48398
    Prev
    Next
    INDEX
    Explanations

    harmful with ?

    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_262k_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
    ፂ
    0.45
     نداشت
    0.42
    ᷄
    0.41
     упаков
    0.41
    两
    0.41
     食器
    0.41
     Bevan
    0.40
     விட
    0.40
     llevan
    0.39
     contando
    0.39
    POSITIVE LOGITS
    ดังกล่าว
    0.48
     utilizzare
    0.45
    сел
    0.45
    舸
    0.43
     carénés
    0.42
     open
    0.42
     inclement
    0.42
     refrigerator
    0.41
    এখানে
    0.40
    ച്ചത്
    0.40
    Activations Density 0.002%

    No Known Activations