© 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. 99596
    Prev
    Next
    INDEX
    Explanations

    tools, institutions, drill

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

    tokens after list items

    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
     LOW
    0.46
     deacon
    0.46
     smile
    0.45
     differentials
    0.45
    ළ
    0.44
     CHE
    0.43
     gevolg
    0.43
     diagonalizable
    0.43
     sanitize
    0.43
     dispenser
    0.43
    POSITIVE LOGITS
    平时
    0.46
     фаразлары
    0.46
    之前的
    0.43
     मेहनत
    0.43
    ството
    0.42
     прош
    0.42
    ৪৩
    0.42
    }">${
    0.41
    জান
    0.41
    <blockquote>
    0.41
    Activations Density 0.002%

    No Known Activations