© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55266
    Prev
    Next
    INDEX
    Explanations

    framework for Skripsi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bragging
    0.49
     👌
    0.46
    🛥
    0.44
    Donnell
    0.44
    Pete
    0.43
     flattered
    0.41
     começar
    0.41
    Yeah
    0.40
    𝗱
    0.40
    𝘥
    0.40
    POSITIVE LOGITS
     ‘
    0.43
     “
    0.42
     Biod
    0.40
     “‘
    0.39
     technolog
    0.38
     mok
    0.37
     SPA
    0.37
     társ
    0.37
     interview
    0.36
     SP
    0.36
    Activations Density 0.003%

    No Known Activations