© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 57421
    Prev
    Next
    INDEX
    Explanations

    harmful negative destructiv damage

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

    negative outcomes or problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     สะ
    0.49
     τρί
    0.49
    🍭
    0.47
                                  
    0.46
     Bakery
    0.45
    四个
    0.44
    📐
    0.44
    🥫
    0.44
     депозит
    0.43
    อร์
    0.43
    POSITIVE LOGITS
     anthropogenic
    0.62
     polluted
    0.60
     degraded
    0.59
     neoplasms
    0.57
     extremist
    0.57
     carcinogenesis
    0.55
     murderous
    0.55
     malignant
    0.54
     devastated
    0.54
     abducted
    0.54
    Activations Density 0.000%

    No Known Activations