© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 1288
    Prev
    Next
    INDEX
    Explanations

    hosts: `

    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
    🧖
    0.38
    (($
    0.38
    パッド
    0.38
    Inline
    0.38
    Ford
    0.37
    以此
    0.37
    Plaintiff
    0.37
    Quick
    0.37
    Ⲟ
    0.36
    াহ্ম
    0.36
    POSITIVE LOGITS
     ./
    0.59
     ../
    0.52
    ./
    0.49
    ../
    0.42
     Numerical
    0.42
     uns
    0.41
     ~/.
    0.41
     Dynamical
    0.41
     Amounts
    0.41
     ~/
    0.41
    Activations Density 0.000%

    No Known Activations