© 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. 28958
    Prev
    Next
    INDEX
    Explanations

    superseding agreements

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

    new data, representing

    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
     o
    0.44
     ln
    0.44
     Boeing
    0.41
     zan
    0.41
     lu
    0.41
     Nederland
    0.40
     വ്യാപ
    0.39
     j
    0.39
    }%
    0.39
     lump
    0.39
    POSITIVE LOGITS
    ات
    0.53
    稦
    0.51
    вей
    0.49
    ೋತಿ
    0.49
    䛊
    0.49
     failings
    0.48
    ಿಂದ
    0.46
    ЛА
    0.46
    犃
    0.46
    енти
    0.46
    Activations Density 0.000%

    No Known Activations