© 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. 21125
    Prev
    Next
    INDEX
    Explanations

    assign or assignment

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

    assigns names or values

    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
    ية
    0.88
     rij
    0.74
    ut
    0.68
    يات
    0.68
     dậy
    0.66
     információ
    0.64
    壘
    0.64
     అ
    0.63
     Angaben
    0.63
    }})^{
    0.63
    POSITIVE LOGITS
    assign
    1.16
    Assign
    1.14
     Assign
    1.13
    assigned
    1.10
     assign
    1.08
     assigned
    1.03
     assigns
    1.01
     Assigned
    0.99
     assignment
    0.97
    Assignment
    0.97
    Activations Density 0.061%

    No Known Activations