© 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. 34-GEMMASCOPE-RES-131K
    7. 64842
    Prev
    Next
    INDEX
    Explanations

    mean or rude behavior

    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
    ʧ
    -0.82
     insanity
    -0.81
     Ayres
    -0.78
    tingen
    -0.77
    good
    -0.77
    riften
    -0.77
     nao
    -0.76
    ارض
    -0.76
     mirando
    -0.76
    χυ
    -0.76
    POSITIVE LOGITS
     rude
    2.53
     cruel
    2.17
    Rude
    2.13
    cruel
    2.11
     unkind
    2.11
    rude
    2.06
     insensitive
    1.91
     Rude
    1.91
     mean
    1.90
    Cruel
    1.80
    Activations Density 0.040%

    No Known Activations