© 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-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 32119
    Prev
    Next
    INDEX
    Explanations

    George Eliot quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    с
    1.42
    ε
    1.33
    た
    1.30
    off
    1.27
    ў
    1.27
    нова
    1.23
    ☻
    1.20
    э
    1.20
    ل
    1.18
     труда
    1.16
    POSITIVE LOGITS
    습니다
    1.57
    이제
    1.34
     maravill
    1.30
    いた
    1.29
    DebugInformation
    1.26
     izgrad
    1.25
    ان
    1.24
     sufrido
    1.24
    Clique
    1.24
    ยนตร์
    1.23
    Activations Density 0.000%

    No Known Activations