© 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. 227866
    Prev
    Next
    INDEX
    Explanations

    money, travel, and products

    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
    ks
    0.56
    کس
    0.51
    ک
    0.48
    sk
    0.47
    スの
    0.46
    定める
    0.44
    we
    0.44
    e
    0.43
    wn
    0.43
    融
    0.42
    POSITIVE LOGITS
     esempl
    0.55
     ansch
    0.54
     كتب
    0.54
     prendere
    0.54
     كتابه
    0.53
     kitabı
    0.52
     absch
    0.50
     aldı
    0.50
     ㅏ
    0.50
     incluyen
    0.48
    Activations Density 0.000%

    No Known Activations