© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13955
    Prev
    Next
    INDEX
    Explanations

    making requests

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

    request

    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_16k_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
    য়া
    0.61
    ра
    0.59
    는
    0.58
    لم
    0.58
    <unused434>
    0.56
    рованной
    0.55
    <unused2141>
    0.55
     constitut
    0.55
     consenting
    0.54
    は
    0.54
    POSITIVE LOGITS
     Request
    1.34
    Request
    1.22
     Requests
    1.20
     REQUEST
    1.10
    request
    1.05
    Requests
    1.01
     requests
    1.00
     request
    1.00
    REQUEST
    0.99
    d
    0.96
    Activations Density 0.148%

    No Known Activations