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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-65K
    4. 874
    Prev
    Next
    INDEX
    Explanations

    declining harmful requests based on purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     barang
    0.82
    l
    0.78
    w
    0.77
     algum
    0.73
    iertos
    0.72
     privada
    0.70
    j
    0.69
    wind
    0.69
    但不
    0.68
    บุ
    0.68
    POSITIVE LOGITS
    riad
    0.92
    corrh
    0.89
    ॓
    0.87
     मानना
    0.87
    য়দ
    0.83
    ວຍ
    0.82
    mathbf
    0.82
     Warszawie
    0.81
    Adv
    0.80
    aulay
    0.80
    Activations Density 0.151%

    No Known Activations