© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138245
    Prev
    Next
    INDEX
    Explanations

    explaining AI model training

    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
    moh
    0.49
    inct
    0.47
     convivial
    0.47
     geographically
    0.45
     serius
    0.44
     $*
    0.44
     encouraged
    0.44
     Petra
    0.43
    %@",
    0.43
    ponible
    0.43
    POSITIVE LOGITS
    عی
    0.45
    ฤ
    0.44
     acceleration
    0.44
    예
    0.44
     ):
    0.43
    Λ
    0.43
    Глав
    0.43
    훈련
    0.42
    </td>
    0.42
    asem
    0.42
    Activations Density 0.005%

    No Known Activations