© 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
    3. Gemma-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 70246
    Prev
    Next
    INDEX
    Explanations

    to improve, find, teach, monitor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
     lichaam
    1.58
    łaszcza
    1.47
     شخصیت
    1.43
    akter
    1.42
     loke
    1.42
     jut
    1.42
     cuerpo
    1.42
    맹
    1.39
     Kopf
    1.38
     setUser
    1.37
    POSITIVE LOGITS
     eradication
    1.57
     studying
    1.46
     investigating
    1.41
     renovating
    1.41
     detectors
    1.34
     investigations
    1.28
     investigation
    1.22
     decommissioning
    1.22
     decompositions
    1.22
     monitoring
    1.21
    Activations Density 0.007%

    No Known Activations