© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2160
    Prev
    Next
    INDEX
    Explanations

    saving files and data

    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
    𝐝
    3.65
    𝐬
    3.38
    𝐱
    3.37
    𝐧
    3.14
    𝐫
    3.05
    𝐭
    3.02
    gameOver
    2.97
    是因为
    2.95
    𝐚
    2.95
    startY
    2.86
    POSITIVE LOGITS
    л
    2.94
    ב
    2.92
    InstanceState
    2.42
     sake
    2.40
    াল
    2.38
     iba
    2.37
    amt
    2.37
    aniye
    2.36
    ালন
    2.35
    로
    2.26
    Activations Density 0.210%

    No Known Activations