© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2828
    Prev
    Next
    INDEX
    Explanations

    age, especially under

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctic
    0.65
    omey
    0.65
    楽
    0.64
    кар
    0.64
    ấc
    0.63
    ouw
    0.63
     /\.
    0.63
    ⊃
    0.62
    benzoic
    0.60
     sinar
    0.59
    POSITIVE LOGITS
     age
    2.79
     Age
    2.49
    Age
    2.43
     ages
    2.28
    年龄
    2.18
     edad
    2.17
     younger
    2.13
     young
    2.12
     aged
    2.12
     âge
    2.12
    Activations Density 0.684%

    No Known Activations