© 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. 25552
    Prev
    Next
    INDEX
    Explanations

    heterosexual and straight orientations

    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
    cycline
    -0.81
    āciju
    -0.74
    újo
    -0.74
     kab
    -0.73
    ayashi
    -0.71
    enschappelijke
    -0.69
    partiet
    -0.69
    halten
    -0.69
    Mej
    -0.69
    veau
    -0.68
    POSITIVE LOGITS
     heterosexual
    4.28
     straight
    4.06
    Straight
    3.56
    straight
    3.47
     Straight
    3.45
     heter
    3.41
    heter
    3.17
     Hetero
    3.11
     hetero
    3.11
    Hetero
    2.77
    Activations Density 0.064%

    No Known Activations