© 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. 135040
    Prev
    Next
    INDEX
    Explanations

    parental involvement and attitudes

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

    parents and families

    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
    养老
    0.46
     забе
    0.42
     ζωή
    0.42
    IDENTITY
    0.42
    ್ರ
    0.41
     איי
    0.41
    㝢
    0.41
    ri
    0.40
    贖
    0.40
     приложение
    0.40
    POSITIVE LOGITS
     Parents
    0.72
     Families
    0.66
     Parental
    0.64
     parents
    0.63
     Parent
    0.61
     parent
    0.58
     अभिभाव
    0.58
     অভিভাবকদের
    0.57
    Parents
    0.57
    parents
    0.57
    Activations Density 0.098%

    No Known Activations