© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 56827
    Prev
    Next
    INDEX
    Explanations

    subtle infiltration and precise information

    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
    А
    0.42
    <0x0D>
    0.41
     countries
    0.41
    {
    0.40
    section
    0.40
    \
    0.40
    }$.
    0.40
     \
    0.39
    <0x80>
    0.39
     favorable
    0.37
    POSITIVE LOGITS
     앱
    0.44
     andDevice
    0.44
     الحياة
    0.44
     निरंतर
    0.43
     ermög
    0.42
    设备的
    0.42
     ऐप
    0.42
    你应该
    0.42
    或其他
    0.41
    tdev
    0.41
    Activations Density 0.003%

    No Known Activations