© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79950
    Prev
    Next
    INDEX
    Explanations

    bolding punctuation and sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     внима
    0.47
    하고
    0.46
    гами
    0.45
    짊
    0.44
    בים
    0.44
     можно
    0.43
     пода
    0.43
    бре
    0.43
    आव
    0.43
    У
    0.43
    POSITIVE LOGITS
     highlighting
    0.47
     Fish
    0.46
    ],
    0.44
     fish
    0.43
     l
    0.42
     discovered
    0.42
     Pa
    0.42
    的是
    0.42
     fuzzy
    0.42
     Simple
    0.41
    Activations Density 0.005%

    No Known Activations