© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1067
    Prev
    Next
    INDEX
    Explanations

    I am / I don't

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

    Instances of the model’s self-reference—high-activation tokens like "I" and nearby words when the assistant is speaking about itself.

    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
     ignoring
    0.47
    და
    0.43
    Ignoring
    0.43
     Ignoring
    0.43
     Ін
    0.42
    ❻
    0.41
    }<\
    0.41
    წ
    0.41
     barring
    0.40
    ィ
    0.40
    POSITIVE LOGITS
     wouldn
    0.57
     memang
    0.52
     certainly
    0.49
     programmed
    0.47
     glad
    0.45
    確かに
    0.45
     اكيد
    0.45
    明白了
    0.44
     indeed
    0.44
     appreciate
    0.42
    Activations Density 0.010%

    No Known Activations