© 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. 189940
    Prev
    Next
    INDEX
    Explanations

    marriage, accounts, expression, violation

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

    potential pros/cons

    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
     හා
    0.57
     começ
    0.49
     червня
    0.47
     मस्ती
    0.47
     resetCounters
    0.47
     müşter
    0.47
     adrenalin
    0.46
    楞
    0.46
    folders
    0.46
     swirling
    0.46
    POSITIVE LOGITS
     MANAGEMENT
    0.45
    ান্য
    0.44
     OFFICE
    0.44
    q
    0.44
    ים
    0.43
     Институт
    0.43
     POINT
    0.43
     THIRD
    0.43
     third
    0.42
    显然
    0.42
    Activations Density 0.000%

    No Known Activations