© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 40172
    Prev
    Next
    INDEX
    Explanations

    speculative and experimental developments

    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_65k_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
    ۔
    0.52
    vée
    0.45
    стина
    0.43
    是
    0.43
    عد
    0.42
    ίλ
    0.42
     ingest
    0.42
    ilde
    0.42
    الج
    0.42
    astico
    0.42
    POSITIVE LOGITS
     సినిమాలు
    0.48
     হেঁ
    0.46
    )」
    0.44
     местности
    0.44
    ാരണ
    0.43
    あたり
    0.43
    晔
    0.43
     உரிமை
    0.42
     Česk
    0.42
    儒
    0.42
    Activations Density 0.005%

    No Known Activations