© 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. 28174
    Prev
    Next
    INDEX
    Explanations

    hyena and leaks

    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_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
     knots
    0.50
     quick
    0.47
     ovens
    0.45
     knot
    0.44
     สะ
    0.42
    quick
    0.42
    avoid
    0.41
    烘
    0.41
    隠
    0.41
    aving
    0.40
    POSITIVE LOGITS
    泄漏
    0.75
    泄
    0.72
     leaking
    0.71
    洩
    0.71
     leaked
    0.70
     whistleblower
    0.70
     leak
    0.66
     divulgação
    0.66
     Leak
    0.63
    Leak
    0.63
    Activations Density 0.040%

    No Known Activations