© 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. 156619
    Prev
    Next
    INDEX
    Explanations

    results, done, BUILD UP

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

    ordinal numbers and suffixes

    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
    ↵↵
    0.49
     entertained
    0.45
    </th>
    0.44
     apartments
    0.43
    )
    0.43
     Fannie
    0.43
     $$
    0.42
    ิ
    0.42
     into
    0.41
     divide
    0.41
    POSITIVE LOGITS
    kowego
    0.46
    蘄
    0.45
     voglio
    0.44
    覬
    0.43
     सीक्वेंस
    0.42
     området
    0.41
    badlogic
    0.41
     чисто
    0.41
     आओ
    0.41
     чого
    0.41
    Activations Density 0.001%

    No Known Activations