© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 45424
    Prev
    Next
    INDEX
    Explanations

    address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    0.55
     identifiers
    0.54
    )
    0.53
     consents
    0.52
    {
    0.52
    ants
    0.52
    nies
    0.51
    closures
    0.49
    nelle
    0.49
     effortlessly
    0.48
    POSITIVE LOGITS
    Address
    0.67
     Address
    0.66
     I
    0.61
     بُک
    0.58
    地址
    0.58
    下の
    0.58
     address
    0.57
    ной
    0.56
    address
    0.55
    getAddress
    0.55
    Activations Density 0.021%

    No Known Activations