© 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. 138402
    Prev
    Next
    INDEX
    Explanations

    copyright notices and contact details

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

    Sources

    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
     实
    0.46
    乡村
    0.44
    實
    0.41
    墙
    0.40
    UNITY
    0.40
    实
    0.39
    섣
    0.39
    梩
    0.39
    лович
    0.38
    𝘦
    0.38
    POSITIVE LOGITS
     Coil
    0.41
     tuvieron
    0.40
    avali
    0.38
     JW
    0.38
    ỗi
    0.37
    otyp
    0.37
     devs
    0.37
     })),
    0.36
     copied
    0.36
    コピー
    0.36
    Activations Density 0.001%

    No Known Activations