© 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. 16-GEMMASCOPE-2-RES-262K
    7. 49646
    Prev
    Next
    INDEX
    Explanations

    Baywatch actress or lifeguard

    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_16_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
     canc
    0.57
     ASAP
    0.56
     LRT
    0.54
    :
    0.54
     NFT
    0.54
     Spani
    0.53
     LSM
    0.52
     ONLY
    0.51
     konkre
    0.51
     necrotic
    0.51
    POSITIVE LOGITS
     څ
    0.57
     বাহিনীর
    0.56
    ể
    0.56
    Nombre
    0.54
    重要な
    0.54
     Sicherheits
    0.52
     ನೀರಿನ
    0.52
    Safety
    0.52
    ньому
    0.52
    ከላከ
    0.51
    Activations Density 0.004%

    No Known Activations