© 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. 163435
    Prev
    Next
    INDEX
    Explanations

    domestic travel, adoption, child

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

    roles and responsibilities

    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
     पाएं
    0.52
    }\{
    0.51
     Wille
    0.49
     weißen
    0.46
     rispett
    0.46
    knit
    0.45
    Ľ
    0.45
     කර
    0.45
    めで
    0.45
     হেতু
    0.45
    POSITIVE LOGITS
    ش
    0.51
     achat
    0.49
    ون
    0.49
     years
    0.48
    ین
    0.48
     segunda
    0.48
    ლების
    0.47
     tipo
    0.44
    पण
    0.44
    सिस
    0.43
    Activations Density 0.001%

    No Known Activations