Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 53048
    Prev
    Next
    INDEX
    Explanations

    your name or document title

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    兼用
    0.82
     ably
    0.79
     But
    0.79
     snork
    0.78
     lakes
    0.78
    .”
    0.77
    ).”
    0.76
    ፤
    0.75
     sink
    0.75
     volcanoes
    0.75
    POSITIVE LOGITS
    {\
    1.85
    Department
    1.40
    School
    1.34
    {
    1.28
     {\
    1.26
    University
    1.24
    <!--
    1.21
    College
    1.18
    Course
    1.18
    Technical
    1.17
    Activations Density 0.001%

    No Known Activations