© 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. 62711
    Prev
    Next
    INDEX
    Explanations

    average household income and composition

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

    callbacks, for, Man, Update, Similar, right, /, Hits

    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
     complicates
    0.53
     senjata
    0.46
    文章
    0.45
    源
    0.45
    措施
    0.43
     armazenamento
    0.43
     authorisation
    0.43
    入手
    0.43
    、
    0.43
    方法
    0.41
    POSITIVE LOGITS
    たちは
    0.56
    ओं
    0.55
    ähn
    0.50
    たちが
    0.48
    ун
    0.48
     შორის
    0.46
    whom
    0.46
    がいる
    0.46
     residing
    0.46
    ücke
    0.46
    Activations Density 0.000%

    No Known Activations