© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 1933
    Prev
    Next
    INDEX
    Explanations

    dangerous and horrific content

    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_16_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
    માં
    0.74
    ку
    0.71
    Tn
    0.70
    A
    0.68
    ㅋ
    0.67
     रोमांटिक
    0.65
    ায়
    0.65
    Про
    0.64
    ೋ
    0.64
    ال
    0.63
    POSITIVE LOGITS
    .
    1.18
    at
    0.81
    -
    0.69
    ↵
    0.68
     jeopard
    0.68
    2
    0.67
     cruel
    0.66
    ۲
    0.65
    al
    0.59
    atical
    0.58
    Activations Density 1.422%

    No Known Activations