© 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. 26636
    Prev
    Next
    INDEX
    Explanations

    age

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

    age or old

    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
    ツール
    0.46
    ଢ
    0.46
    ARMA
    0.46
     বৃষ্টির
    0.46
    AWS
    0.45
    剱
    0.45
    বে
    0.44
    MO
    0.44
     ပ
    0.44
    Habitat
    0.43
    POSITIVE LOGITS
    年龄
    1.46
     edad
    1.44
     age
    1.40
    年齢
    1.38
     उम्र
    1.31
     idade
    1.30
     Age
    1.29
     âge
    1.29
     อายุ
    1.27
     வயது
    1.20
    Activations Density 0.104%

    No Known Activations