© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 114887
    Prev
    Next
    INDEX
    Explanations

    young people and adults

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

    youth and young people

    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
     изображение
    0.44
     assassinated
    0.43
    情報は
    0.42
    🇪
    0.42
    Typography
    0.42
     текст
    0.42
    መ
    0.41
     資
    0.41
    ране
    0.41
     Informations
    0.40
    POSITIVE LOGITS
     receptacles
    0.47
     yearling
    0.47
     adolescentes
    0.46
    Kids
    0.46
    ocks
    0.45
     kiddos
    0.45
     adults
    0.45
     youngsters
    0.45
     adulti
    0.44
     cages
    0.44
    Activations Density 0.001%

    No Known Activations