© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 213035
    Prev
    Next
    INDEX
    Explanations

    extracting information

    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
    ।’
    0.49
    .​​
    0.46
    ।”
    0.44
    ’।
    0.43
    μέ
    0.42
    ֶ
    0.42
     suoi
    0.42
     rikt
    0.42
     şart
    0.41
    ’;
    0.41
    POSITIVE LOGITS
     Does
    0.57
     Introduction
    0.54
     Theorem
    0.54
     How
    0.52
     Preface
    0.52
     Let
    0.51
     Are
    0.51
     Thank
    0.50
    stackoverflow
    0.50
     What
    0.50
    Activations Density 0.002%

    No Known Activations