© 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. 34-GEMMASCOPE-RES-131K
    7. 57268
    Prev
    Next
    INDEX
    Explanations

    mad followed by other words

    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_34/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
    ROZ
    -0.77
    Contd
    -0.73
    初心者
    -0.73
    nebo
    -0.73
    BYE
    -0.73
    BUMP
    -0.73
    disp
    -0.71
    Nn
    -0.70
     Narciss
    -0.70
     thuật
    -0.69
    POSITIVE LOGITS
    Mad
    1.53
     MAD
    1.44
     Mad
    1.44
     mad
    1.30
    MAD
    1.27
     scientist
    1.17
    mad
    1.09
     Madsen
    1.08
     Maddox
    1.03
     Madness
    1.01
    Activations Density 0.013%

    No Known Activations