© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72046
    Prev
    Next
    INDEX
    Explanations

    passwords and authentication security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     algunos
    -1.26
     város
    -1.25
     блюдо
    -1.23
     podem
    -1.22
    umbledore
    -1.18
    崛
    -1.18
     ant
    -1.13
     algunas
    -1.09
     estructura
    -1.07
     промо
    -1.07
    POSITIVE LOGITS
     your
    2.11
     täh
    1.41
     you
    1.36
     senin
    1.23
     elektronik
    1.23
     Kristus
    1.18
    licaciones
    1.16
    farms
    1.16
     sinyal
    1.15
    觀眾
    1.14
    Activations Density 0.041%

    No Known Activations