© 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. 15781
    Prev
    Next
    INDEX
    Explanations

    verb after noun

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

    "i'll also add a disclaimer at the end"

    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
    或者
    0.49
     或者
    0.45
    或
    0.45
    ὢ
    0.43
    oss
    0.43
    click
    0.42
    、
    0.42
    oy
    0.42
     औद्योगिक
    0.41
    ，
    0.41
    POSITIVE LOGITS
     đủ
    0.49
     takže
    0.45
     sodass
    0.45
     én
    0.42
     Lé
    0.42
     altre
    0.41
     Č
    0.40
     فه
    0.40
     genoeg
    0.40
     chape
    0.40
    Activations Density 0.000%

    No Known Activations