© 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. 90611
    Prev
    Next
    INDEX
    Explanations

    extreme stress or usage

    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
     impotence
    -0.92
    liches
    -0.89
     bloated
    -0.88
    lijk
    -0.86
    ותו
    -0.86
    encing
    -0.82
    liche
    -0.82
    перь
    -0.80
     workable
    -0.80
    ódz
    -0.79
    POSITIVE LOGITS
     abuse
    2.98
    abuse
    2.42
     Abuse
    2.23
     punishment
    2.19
     abused
    2.14
     abuses
    2.08
     abusive
    1.90
     abusing
    1.80
    Abuse
    1.79
     abuso
    1.60
    Activations Density 0.045%

    No Known Activations