© 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. 7505
    Prev
    Next
    INDEX
    Explanations

    questions about failures or issues

    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
     зло
    0.49
     انرژی
    0.49
     algebraica
    0.49
     obesidad
    0.48
    ቪ
    0.47
     Interessen
    0.47
     Ві
    0.46
     Однако
    0.46
     Zentrum
    0.46
     ausreiche
    0.46
    POSITIVE LOGITS
    j
    0.55
     welding
    0.51
     heating
    0.48
     storage
    0.47
    v
    0.46
     quarantine
    0.46
     günlük
    0.46
     lineage
    0.44
    en
    0.43
    elar
    0.42
    Activations Density 0.011%

    No Known Activations