© 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. 7659
    Prev
    Next
    INDEX
    Explanations

    Walk/ Royal Blue

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

    room names, addresses, job duties

    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
     δεύτε
    0.35
     drugiej
    0.33
    狒
    0.32
     druhé
    0.32
     gdyż
    0.32
     newcom
    0.31
     Nucleaire
    0.31
    শীর
    0.31
     drugim
    0.31
     hänen
    0.30
    POSITIVE LOGITS
    _
    0.50
    and
    0.45
    ="",
    0.45
    /
    0.45
     ,
    0.43
    =
    0.42
    (),
    0.42
     &
    0.40
    :'',
    0.39
    :,
    0.39
    Activations Density 0.029%

    No Known Activations