© 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. 134403
    Prev
    Next
    INDEX
    Explanations

    listings and pm

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

    preventing blocking operations

    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
    лог
    0.48
    लर
    0.46
    妿
    0.46
    華
    0.45
    ísmo
    0.45
    娛樂
    0.44
    楓
    0.43
    })$
    0.43
    鵝
    0.43
    禦
    0.43
    POSITIVE LOGITS
     thrombosis
    0.54
     macrophage
    0.50
     interleukin
    0.50
     sluggish
    0.48
     গ্রহণযোগ্য
    0.47
    แก้ไข
    0.47
     কলেজে
    0.46
     pym
    0.46
     rheumatoid
    0.46
     Ogun
    0.45
    Activations Density 0.000%

    No Known Activations