© 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. 133877
    Prev
    Next
    INDEX
    Explanations

    business and shipping

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

    Stripe architecture scaling accuracy

    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
    ’
    0.64
    س
    0.63
    ↵↵
    0.62
    ↵
    0.55
    '
    0.51
     molti
    0.49
    ع
    0.47
    Heather
    0.46
     contrat
    0.46
    …
    0.46
    POSITIVE LOGITS
     解析
    0.56
     दंग
    0.52
     기존
    0.52
     주고
    0.50
     తాను
    0.49
     gé
    0.49
     පළ
    0.48
    CUSTOMER
    0.47
     явления
    0.47
     తా
    0.46
    Activations Density 0.000%

    No Known Activations