© 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. 10497
    Prev
    Next
    INDEX
    Explanations

    pronoun referring to subject

    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
     ഇത്
    0.46
    頨
    0.41
     সত্যিই
    0.40
     هذا
    0.38
     වලින්
    0.38
     അവരുടെ
    0.37
    𝓙
    0.37
     ಇದು
    0.36
     طبیعی
    0.36
     눈
    0.36
    POSITIVE LOGITS
    zelf
    0.51
     undergoes
    0.46
    ſelf
    0.45
    sef
    0.43
     faithfully
    0.39
    opath
    0.38
     resides
    0.38
     performs
    0.38
    ｓ
    0.37
    spath
    0.36
    Activations Density 0.062%

    No Known Activations