© 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-262K
    7. 17748
    Prev
    Next
    INDEX
    Explanations

    AI model self-identification

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

    Occurrences of the literal token "model" (the metadata/system label that appears in assistant/system message lines).

    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_31_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
     $)$.
    0.44
     تیار
    0.41
     refreshToken
    0.39
    》。
    0.38
     karşınız
    0.38
     digress
    0.38
     zape
    0.37
    ResumeLayout
    0.37
    progressBar
    0.37
    DarkMode
    0.36
    POSITIVE LOGITS
     When
    0.40
     Anything
    0.40
     Ό
    0.40
    When
    0.38
     Infinite
    0.37
     Away
    0.37
    Good
    0.36
     நான்
    0.36
    Anything
    0.36
    Then
    0.36
    Activations Density 0.048%

    No Known Activations