© 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-262K
    7. 45727
    Prev
    Next
    INDEX
    Explanations

    technical documentation and code snippets

    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
     domestic
    0.42
    iddag
    0.38
    狀
    0.38
     √
    0.37
     supermarkets
    0.37
     Sok
    0.37
    ándolo
    0.37
    phis
    0.36
     вид
    0.36
    URLConnection
    0.36
    POSITIVE LOGITS
     स्थलों
    0.45
     কখনই
    0.45
    Does
    0.43
     annotated
    0.43
     Prejudice
    0.42
    从来
    0.40
    韫
    0.40
    袄
    0.40
    не
    0.39
    lint
    0.39
    Activations Density 0.000%

    No Known Activations