© 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. 31-GEMMASCOPE-2-RES-65K
    7. 933
    Prev
    Next
    INDEX
    Explanations

    instances of self-referential language and self-descriptions in responses.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    these are examples

    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_31_width_65k_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
    /
    0.22
    ’
    0.22
    \
    0.20
    -
    0.18
    .
    0.18
    （
    0.16
     Rc
    0.16
    (
    0.16
     (
    0.15
    '
    0.15
    POSITIVE LOGITS
     విధంగా
    0.22
     was
    0.22
     is
    0.21
     ነው
    0.20
    는
    0.19
     был
    0.18
     konuda
    0.18
     makes
    0.18
    ра
    0.18
     అంశ
    0.17
    Activations Density 0.697%

    No Known Activations