© 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. 49748
    Prev
    Next
    INDEX
    Explanations

    come under, when application, your CV

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

    authorization, notification, and specific foreign terms

    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
    l
    0.49
     l
    0.48
    L
    0.47
     Pittsburg
    0.46
    N
    0.46
    至于
    0.45
    ال
    0.44
     spat
    0.43
     circulation
    0.42
    j
    0.42
    POSITIVE LOGITS
     уведом
    0.56
    ници
    0.52
     autorización
    0.48
     authorizes
    0.47
     entsprechend
    0.47
     egyéb
    0.46
     incênd
    0.45
     législ
    0.44
    াহতি
    0.44
    ровать
    0.43
    Activations Density 0.000%

    No Known Activations