© 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-16K
    7. 1098
    Prev
    Next
    INDEX
    Explanations

    about and regarding

    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_16k_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
    ீ
    0.47
    ᆷ
    0.45
    }$.
    0.43
     και
    0.43
     มี
    0.42
     व
    0.41
     consonant
    0.41
    ᆫ
    0.41
     จํา
    0.41
    ᆯ
    0.41
    POSITIVE LOGITS
     about
    0.70
     về
    0.66
     hakkında
    0.62
    如何
    0.61
     bagaimana
    0.60
     tentang
    0.59
     how
    0.57
     كيفية
    0.55
    关于
    0.55
     поводу
    0.54
    Activations Density 0.264%

    No Known Activations