© 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. 99286
    Prev
    Next
    INDEX
    Explanations

    Transaction and security concepts

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

    legal security transaction force

    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
    یدن
    0.47
     angios
    0.46
     Celebrate
    0.46
    دن
    0.46
     electromagnet
    0.46
     asymmetries
    0.46
     célébr
    0.45
    憩
    0.45
     उत्सव
    0.44
    ்களுக்கு
    0.44
    POSITIVE LOGITS
    Transaction
    0.54
    security
    0.53
    police
    0.52
    }}>
    0.51
    Tao
    0.50
    Singh
    0.50
    addition
    0.49
    Police
    0.49
    vam
    0.49
    Security
    0.48
    Activations Density 0.000%

    No Known Activations