© 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. 15558
    Prev
    Next
    INDEX
    Explanations

    genuine, harmless, or legitimate

    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_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
     getContentPane
    0.43
     постоянно
    0.41
    Monte
    0.40
    க்கை
    0.40
     satte
    0.40
     ప్రత్య
    0.40
    }\|_{
    0.40
    terus
    0.39
    ondo
    0.39
     ด
    0.38
    POSITIVE LOGITS
     legitimate
    1.27
     harmless
    1.27
     legít
    1.13
     legitimately
    1.10
     innocuous
    1.08
     benign
    1.05
     merely
    1.00
     legitt
    0.98
     innoc
    0.96
     innocent
    0.91
    Activations Density 0.073%

    No Known Activations