© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 4107
    Prev
    Next
    INDEX
    Explanations

    code comments and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
    </h3>
    1.99
    </h1>
    1.59
    ']}
    1.49
    】【
    1.37
    の良い
    1.36
     }}{
    1.36
    </td>
    1.29
    |}
    1.29
     }]
    1.24
    }]
    1.23
    POSITIVE LOGITS
     этот
    1.83
     this
    1.66
     pictured
    1.55
    this
    1.54
    published
    1.51
    之前
    1.48
     heretofore
    1.48
    本
    1.47
     эту
    1.45
     questo
    1.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.