© 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. 245070
    Prev
    Next
    INDEX
    Explanations

    special offers for subscribers and lapsed customers

    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
    󰡕
    0.54
     первом
    0.51
     incógn
    0.50
     стрелецкой
    0.49
     dispers
    0.49
     Dewar
    0.49
     旧
    0.49
    🅘
    0.49
     рассе
    0.48
     着
    0.48
    POSITIVE LOGITS
    Emails
    0.50
    subscription
    0.50
    emails
    0.46
    ր
    0.44
    iteration
    0.44
    ቢያ
    0.44
    ίων
    0.44
    relevant
    0.42
    だったので
    0.42
    ivering
    0.42
    Activations Density 0.000%

    No Known Activations