© 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. 53-GEMMASCOPE-2-RES-262K
    7. 47014
    Prev
    Next
    INDEX
    Explanations

    Sal words

    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_53_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
    )....
    0.43
    <u>
    0.41
    ▄
    0.39
    ราะ
    0.38
    foaf
    0.37
    )…
    0.37
    ětí
    0.37
     practically
    0.36
    anthem
    0.36
    <a>
    0.36
    POSITIVE LOGITS
     respeto
    0.51
     SAL
    0.50
     сала
    0.47
    墮
    0.45
     Respect
    0.42
     Salim
    0.41
     desejo
    0.40
    욕
    0.40
     Colored
    0.39
     desee
    0.39
    Activations Density 0.003%

    No Known Activations