© 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. 96793
    Prev
    Next
    INDEX
    Explanations

    avoid using, Jesus must

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

    Drake

    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
     boilerplate
    0.49
     disgruntled
    0.49
     হয়েছে
    0.48
     технологі
    0.48
    されています
    0.46
    ோ
    0.46
    iert
    0.46
     এতদিন
    0.46
     childish
    0.45
     nefarious
    0.45
    POSITIVE LOGITS
    Debit
    0.49
    P
    0.46
     Clubs
    0.45
    Groups
    0.44
     অনন্য
    0.44
    लाब
    0.43
     Groups
    0.43
    l
    0.43
    De
    0.42
     Ali
    0.42
    Activations Density 0.001%

    No Known Activations