© 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. 115479
    Prev
    Next
    INDEX
    Explanations

    development and personal growth

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

    long-term psychological harm

    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
    ती
    0.45
     encuentros
    0.44
    ቴክ
    0.41
    лежа
    0.40
    ИТ
    0.40
     affords
    0.39
    沣
    0.39
    families
    0.39
     reputations
    0.39
    ጆ
    0.38
    POSITIVE LOGITS
     becoming
    0.60
     became
    0.60
     stunted
    0.57
     development
    0.54
     Eventually
    0.54
     Became
    0.53
     become
    0.53
     menjadi
    0.52
     Develop
    0.52
     eventually
    0.50
    Activations Density 0.026%

    No Known Activations