© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 179952
    Prev
    Next
    INDEX
    Explanations

    celebrity moms

    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
    Negative Logits
    中华
    0.52
     reorgan
    0.52
     Privat
    0.45
    uyente
    0.45
    潘
    0.45
     pretended
    0.45
     worsen
    0.44
    匁
    0.44
     oysters
    0.44
     身
    0.43
    POSITIVE LOGITS
     Land
    0.46
    Land
    0.42
     Landing
    0.42
     Valladolid
    0.41
    GAP
    0.41
    Landing
    0.41
    voices
    0.40
    vars
    0.40
     روست
    0.40
    kommt
    0.40
    Activations Density 0.000%

    No Known Activations