© 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. 201301
    Prev
    Next
    INDEX
    Explanations

    safe and appropriate alternatives

    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
     murderous
    0.53
    ر
    0.47
    นน
    0.43
     Pooling
    0.43
    нами
    0.42
    кого
    0.41
    סף
    0.41
     OnInit
    0.39
    这是一个
    0.39
     Scene
    0.39
    POSITIVE LOGITS
    Peru
    0.53
     riba
    0.52
     הו
    0.51
     बदल
    0.50
     පිළ
    0.50
     הח
    0.48
     ፈ
    0.48
     नैतिकता
    0.48
    ación
    0.47
     acuerdo
    0.47
    Activations Density 0.007%

    No Known Activations