© 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. 212993
    Prev
    Next
    INDEX
    Explanations

    financial concepts or outcomes

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

    describing actions and states

    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
     Selective
    0.46
    廳
    0.45
    。
    0.44
     Mixer
    0.44
    不堪
    0.44
    ठे
    0.43
    紀
    0.43
    批
    0.43
    號
    0.42
     तक
    0.41
    POSITIVE LOGITS
     reflectivity
    0.54
    Catagory
    0.52
     טוב
    0.51
     storia
    0.50
    diss
    0.49
     risultato
    0.48
    Diss
    0.48
     terzo
    0.48
     multa
    0.48
    catalyzed
    0.47
    Activations Density 0.000%

    No Known Activations