© 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. 3294
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms

    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
     reliable
    1.20
     valuable
    1.19
     ¬
    1.18
     sacred
    1.11
     precious
    1.10
     sacrificial
    1.10
     scarce
    1.07
     snowfall
    1.07
     mandatory
    1.06
     purely
    1.06
    POSITIVE LOGITS
    leszt
    1.61
    laszt
    1.47
     قامت
    1.44
    ới
    1.42
     时尚
    1.40
    ùm
    1.39
     该
    1.38
    ták
    1.38
     方
    1.38
     قوه
    1.37
    Activations Density 0.198%

    No Known Activations