© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 223476
    Prev
    Next
    INDEX
    Explanations

    capitalism, "thinking", Civil Conflict

    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_40_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
    convolution
    0.42
    ል።
    0.41
     zoos
    0.40
    Wheel
    0.40
    predictions
    0.40
     quadrants
    0.40
     convolutions
    0.40
    &-
    0.40
    ሉ።
    0.39
    Predictions
    0.39
    POSITIVE LOGITS
    encies
    0.45
    hani
    0.40
    ències
    0.39
    甚至
    0.38
    zymy
    0.37
     glories
    0.37
    彷
    0.37
     య
    0.36
     імені
    0.36
     perched
    0.36
    Activations Density 0.000%

    No Known Activations