© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9763
    Prev
    Next
    INDEX
    Explanations

    sexual abuse, former staff, six Palestinians

    np_acts-logits-general · gemini-2.5-flash-lite

    specific entities and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    辂
    0.44
     Anzahl
    0.43
     Ispol
    0.42
     сущ
    0.41
     അന്ന
    0.41
     dSample
    0.40
    |.|.|
    0.39
    வ்வளவு
    0.38
     wobei
    0.38
    贰百
    0.38
    POSITIVE LOGITS
     coronavirus
    0.50
     billionaire
    0.42
    coronavirus
    0.39
     controvers
    0.38
     nightclub
    0.37
    -
    0.37
     cybersecurity
    0.36
     eurozone
    0.36
     bitcoin
    0.35
     liquefied
    0.34
    Activations Density 0.157%

    No Known Activations