© 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. 73426
    Prev
    Next
    INDEX
    Explanations

    financing dependency

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

    secures/radius/infect/suppliers

    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
    denum
    0.51
    gave
    0.49
    (),"
    0.48
    bladder
    0.47
    assian
    0.47
    fought
    0.47
    funeral
    0.46
    ͹
    0.46
    ền
    0.46
    folder
    0.46
    POSITIVE LOGITS
     kapital
    0.53
     IN
    0.47
     umet
    0.47
     circulating
    0.46
     SMAD
    0.45
     THAT
    0.45
     Examiners
    0.45
     BY
    0.45
     circul
    0.45
     ohne
    0.44
    Activations Density 0.001%

    No Known Activations