© 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. 22-GEMMASCOPE-2-RES-262K
    4. 639
    Prev
    Next
    INDEX
    Explanations

    permanent vs temporary state

    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_22_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
    𝐝
    0.90
    早速
    0.89
    imming
    0.88
     Aware
    0.85
    Swipe
    0.84
    counted
    0.84
    𝐞
    0.84
    𝐬
    0.84
    ገል
    0.83
     Accordingly
    0.83
    POSITIVE LOGITS
    性的
    1.21
    性和
    1.08
     isotope
    1.02
    性が
    0.97
    性の
    0.95
     moored
    0.95
     fixture
    0.93
     structures
    0.91
     residents
    0.90
     solutions
    0.90
    Activations Density 0.136%

    No Known Activations