© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 3345
    Prev
    Next
    INDEX
    Explanations

    GPT models

    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_all/layer_41_width_262k_l0_big
    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
    Lora
    0.40
     ير
    0.38
    (__('
    0.38
    ('%
    0.36
    éraire
    0.36
     '_'
    0.36
    anceled
    0.35
    ဵ
    0.35
    erving
    0.34
    陘
    0.34
    POSITIVE LOGITS
     turbo
    0.87
     Turbo
    0.79
    Turbo
    0.75
     turb
    0.72
    turbo
    0.71
     Turb
    0.63
     turbocharged
    0.61
    turb
    0.61
     turban
    0.60
    Turb
    0.59
    Activations Density 0.004%

    No Known Activations