© 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. 139522
    Prev
    Next
    INDEX
    Explanations

    context specific phrases

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

    affecting many, rare, rebuild

    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
     collector
    0.46
     chuyển
    0.46
    これで
    0.45
    رو
    0.45
    近い
    0.45
     columnist
    0.44
    <unused2172>
    0.44
     complication
    0.42
    かん
    0.42
     Collector
    0.42
    POSITIVE LOGITS
    gg
    0.57
    auen
    0.52
    şi
    0.47
    aca
    0.46
    newTask
    0.46
    atern
    0.46
    ger
    0.46
    ten
    0.45
    ypes
    0.44
    </td>
    0.43
    Activations Density 0.000%

    No Known Activations