© 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. 41542
    Prev
    Next
    INDEX
    Explanations

    thank you messages

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

    financial policies and divisions

    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
     mother
    0.53
    泗
    0.48
    aned
    0.45
    チール
    0.45
    gespr
    0.45
    曼
    0.44
     نړۍ
    0.44
    ným
    0.43
     Mutter
    0.43
    aarr
    0.43
    POSITIVE LOGITS
    קס
    0.47
    вшего
    0.46
    да
    0.45
     綿
    0.44
     атмос
    0.44
     Константи
    0.44
    Utils
    0.42
     আত
    0.42
    Constants
    0.42
     атмосфер
    0.41
    Activations Density 0.000%

    No Known Activations