© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 53316
    Prev
    Next
    INDEX
    Explanations

    danger and danger variations

    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_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
    1
    0.48
    Factors
    0.47
    D
    0.45
    Officer
    0.45
    ž
    0.45
    ，
    0.44
     बचाने
    0.43
    ж
    0.42
    ఎ
    0.42
    CHANT
    0.41
    POSITIVE LOGITS
    ously
    0.79
    ous
    0.70
     dangereux
    0.63
    dangerous
    0.62
     peligros
    0.61
     dangerous
    0.60
     dangere
    0.59
     berbahaya
    0.58
     Dangerous
    0.57
     опас
    0.54
    Activations Density 0.025%

    No Known Activations