© 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. 174105
    Prev
    Next
    INDEX
    Explanations

    travel tickets; hard work; drug deaths

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

    including lists or examples

    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
    ম
    0.42
    मस
    0.42
    ноу
    0.40
     COMMUN
    0.40
    স
    0.40
    smanship
    0.40
    মস
    0.38
    मुझे
    0.38
    S
    0.38
    راث
    0.38
    POSITIVE LOGITS
     przykład
    0.51
     wrink
    0.50
     wersji
    0.50
     roku
    0.49
    ブン
    0.49
     llevaron
    0.49
     duet
    0.47
    rzym
    0.47
    сцю
    0.47
    वर्षी
    0.47
    Activations Density 0.000%

    No Known Activations