© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39259
    Prev
    Next
    INDEX
    Explanations

    attack the source

    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
     других
    -0.92
     інших
    -0.91
     from
    -0.91
     other
    -0.88
     among
    -0.87
     counter
    -0.87
     기
    -0.86
    transpiration
    -0.86
     across
    -0.84
     according
    -0.84
    POSITIVE LOGITS
     itself
    1.38
     selve
    1.30
    本身
    1.23
     сами
    1.22
     samot
    1.18
    }],
    1.13
    >',
    1.11
    ="";
    1.09
     what
    1.04
     själva
    1.03
    Activations Density 0.055%

    No Known Activations