© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 10239
    Prev
    Next
    INDEX
    Explanations

    pretend to be

    np_acts-logits-general · gemini-2.5-flash-lite

    technical/code-related content and explanations — e.g., code/list tokens, brackets and hashes, and phrases introducing or explaining code or debugging.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    R
    1.00
    B
    0.91
    D
    0.85
    L
    0.81
    H
    0.80
    ilience
    0.80
    S
    0.79
    P
    0.75
    K
    0.73
    čio
    0.73
    POSITIVE LOGITS
     qualquer
    1.04
     artículos
    0.95
     Fällen
    0.92
     porque
    0.89
     artigos
    0.88
    тся
    0.87
     Fakultas
    0.87
     Eindruck
    0.87
     advogado
    0.85
     typos
    0.85
    Activations Density 5.358%

    No Known Activations