© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59773
    Prev
    Next
    INDEX
    Explanations

    abuse

    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
     =
    -0.97
     piac
    -0.94
     amassed
    -0.90
     ”
    -0.90
     usual
    -0.88
    жения
    -0.85
    将会
    -0.85
    n
    -0.84
     bloke
    -0.83
     desires
    -0.83
    POSITIVE LOGITS
     abuse
    1.70
    abuse
    1.59
     Abuse
    1.45
    Abuse
    1.40
     abusive
    1.24
     abused
    1.19
     of
    1.18
     abusing
    1.16
     Abu
    1.09
     abuso
    1.07
    Activations Density 0.013%

    No Known Activations