© 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. 17-GEMMASCOPE-2-RES-16K
    4. 1932
    Prev
    Next
    INDEX
    Explanations

    behind, beneath, beyond

    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_17_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
     emple
    1.46
    링
    1.44
     r
    1.42
     entrare
    1.40
    ために
    1.36
     impede
    1.29
     Вообще
    1.29
    и
    1.25
     cui
    1.24
     στοι
    1.24
    POSITIVE LOGITS
     reproach
    1.77
    枱
    1.57
    帼
    1.56
     FERC
    1.56
    ジン
    1.55
    ों
    1.55
    toBeTruthy
    1.55
    ំហ
    1.54
    erees
    1.53
    compre
    1.53
    Activations Density 0.203%

    No Known Activations