© 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. 40-GEMMASCOPE-2-RES-262K
    7. 3879
    Prev
    Next
    INDEX
    Explanations

    personal possessions or attributes

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of personal possessive pronouns used to express ownership or address (e.g., "my", "your", "our").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     zowel
    0.17
    特性
    0.17
     both
    0.16
    became
    0.16
    Both
    0.15
    特点
    0.15
    以
    0.15
     opined
    0.14
     ([
    0.14
     became
    0.13
    POSITIVE LOGITS
     own
    0.32
     grandmother
    0.22
     suspicions
    0.21
     favorite
    0.21
     propias
    0.20
    riad
    0.20
     fingertips
    0.20
     favourite
    0.20
     Own
    0.20
     eigenen
    0.20
    Activations Density 0.187%

    No Known Activations