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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 40621
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by nouns

    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
    of
    1.02
    ete
    0.98
     טוב
    0.98
     한
    0.93
     은
    0.93
    og
    0.93
    ren
    0.88
    umi
    0.88
     만
    0.87
    ick
    0.87
    POSITIVE LOGITS
    л
    0.93
    ي
    0.86
    Լ
    0.84
    ᱥ
    0.82
     presidenta
    0.75
    P
    0.75
     legislação
    0.75
    ﻜ
    0.75
     slumped
    0.75
    ק
    0.75
    Activations Density 0.003%

    No Known Activations