© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11668
    Prev
    Next
    INDEX
    Explanations

    acknowledging or condemning actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ப்பட்ட
    2.61
    ្ឋ
    2.60
    रिपोर्ट
    2.59
    שים
    2.58
     gli
    2.51
    ધન
    2.49
    ﻭ
    2.42
    fat
    2.30
    offs
    2.29
    UNDER
    2.28
    POSITIVE LOGITS
    მწიფ
    2.71
    ‌‌
    2.61
    𝑎
    2.52
    𝑒
    2.47
    elve
    2.46
    ‌
    2.46
    ｅ
    2.46
    𝑠
    2.44
     sixteen
    2.35
    ᴢ
    2.34
    Activations Density 0.001%

    No Known Activations