© 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. 10044
    Prev
    Next
    INDEX
    Explanations

    age ranges

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

    age and age ranges

    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
    Possible
    0.46
    possible
    0.45
    T
    0.44
    B
    0.42
    for
    0.41
    3
    0.41
     beam
    0.41
    Valid
    0.41
    Y
    0.41
    valid
    0.40
    POSITIVE LOGITS
     berusia
    0.98
     ages
    0.90
     возрасте
    0.89
     edad
    0.87
     tuổi
    0.86
     उम्र
    0.84
     edades
    0.84
     âge
    0.83
     usia
    0.82
    年龄
    0.81
    Activations Density 0.034%

    No Known Activations