© 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-262K
    7. 93954
    Prev
    Next
    INDEX
    Explanations

    bolded/special characters and lists

    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
    attlist
    0.50
    膽
    0.42
    occhi
    0.42
    㴬
    0.41
    ភ្ល
    0.41
    ਮੀ
    0.40
    setminus
    0.40
     канди
    0.40
    Embarked
    0.40
    MemberList
    0.40
    POSITIVE LOGITS
    赵
    0.50
     Hu
    0.43
     Zhao
    0.43
     Dacă
    0.43
     Bartosz
    0.42
     configur
    0.42
    然后
    0.42
     Session
    0.42
     Cookie
    0.42
     Config
    0.42
    Activations Density 0.006%

    No Known Activations