© 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. 59546
    Prev
    Next
    INDEX
    Explanations

    starts or creations

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

    candy floss trees or price changes

    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
     回転
    0.46
     "-"]
    0.43
     証明
    0.42
     relem
    0.41
    हायला
    0.41
    gnię
    0.41
    ਸੀਂ
    0.41
     menutup
    0.40
     एप्ली
    0.40
     executar
    0.40
    POSITIVE LOGITS
    源
    0.42
    political
    0.41
    ​
    0.39
    나
    0.38
     Seen
    0.38
    ۱۹
    0.37
    politics
    0.37
     )
    0.37
     위
    0.37
    序
    0.37
    Activations Density 0.000%

    No Known Activations