© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203907
    Prev
    Next
    INDEX
    Explanations

    I can make mistakes

    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
    izzard
    0.52
    ₵
    0.50
     ನೋಡ
    0.49
    ACING
    0.49
    ☬
    0.47
    ANTH
    0.45
    ERICK
    0.45
     지금
    0.44
     ಕಾ
    0.44
     ಕಾಣ
    0.43
    POSITIVE LOGITS
    年
    0.47
     Afro
    0.41
     เอ่อ
    0.41
    ب
    0.41
     основ
    0.40
     maioria
    0.39
    वर्षी
    0.39
     बहुमत
    0.39
     reacción
    0.38
    ्लादेश
    0.38
    Activations Density 0.007%

    No Known Activations