© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 186231
    Prev
    Next
    INDEX
    Explanations

    stereotypes

    np_acts-logits-general · gemini-2.5-flash-lite

    stereotypes and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存储
    0.45
     paw
    0.45
     THOR
    0.45
    ΠΑ
    0.45
     Colbert
    0.45
    农业
    0.44
    呈
    0.44
    ဂျ
    0.44
    ும
    0.44
     BAI
    0.43
    POSITIVE LOGITS
     Stere
    0.46
    ৩৭
    0.46
     दृष्टिकोण
    0.46
    oping
    0.46
     stereotypes
    0.45
     stereotypical
    0.44
     stereotype
    0.43
    នឹង
    0.43
    ှ
    0.42
    fh
    0.42
    Activations Density 0.001%

    No Known Activations