© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90114
    Prev
    Next
    INDEX
    Explanations

    Python code examples, Portuguese, speedboat, trash cans

    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
    down
    0.46
    恝
    0.44
    fundamental
    0.42
    ও
    0.42
    碎片
    0.42
    respons
    0.41
    هِ
    0.41
    branding
    0.41
    그
    0.40
    fortun
    0.40
    POSITIVE LOGITS
     atrak
    0.53
     plowed
    0.49
     są
    0.48
    கர
    0.46
     permettent
    0.46
     নিষেধ
    0.45
     vegan
    0.45
     lazer
    0.45
     temporada
    0.44
     Джей
    0.44
    Activations Density 0.003%

    No Known Activations