© 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-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-16K
    4. 570
    Prev
    Next
    INDEX
    Explanations

    code blocks and placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_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
    нд
    2.34
    ด์
    2.11
    ations
    2.10
    ка
    2.04
    ко
    2.01
    ные
    1.99
    ة
    1.97
    ное
    1.91
    ক্ষ
    1.90
    дови
    1.87
    POSITIVE LOGITS
     }_{
    2.25
    fileID
    2.05
     }^{\
    2.02
     potro
    2.00
     MODKEY
    1.85
     }^{*}
    1.81
     }+\
    1.76
    /}
    1.74
     }^{
    1.74
    substack
    1.74
    Activations Density 0.320%

    No Known Activations