© 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. 145124
    Prev
    Next
    INDEX
    Explanations

    cat meat, sheds are, stabilized

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

    replacing or minimizing data loss

    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
    includegraphics
    0.47
     breathtaking
    0.43
     affidavit
    0.42
     л
    0.42
     profiling
    0.41
     magnificence
    0.41
     remarkable
    0.41
     greens
    0.40
     stunning
    0.40
     KENT
    0.40
    POSITIVE LOGITS
     Otra
    0.52
    Tareas
    0.50
     حقی
    0.50
     Productos
    0.49
    唥
    0.48
     Kader
    0.48
     Kita
    0.47
     শাস্ত
    0.47
     Risiko
    0.47
     قریب
    0.46
    Activations Density 0.001%

    No Known Activations