© 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. 12638
    Prev
    Next
    INDEX
    Explanations

    code comments and return types

    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
    മ്പ്
    0.39
     соло
    0.38
    ляр
    0.38
    ж
    0.38
     neighbourhoods
    0.37
     cot
    0.36
    硐
    0.36
    َال
    0.35
     ме
    0.35
     neighbourhood
    0.35
    POSITIVE LOGITS
     chased
    0.40
    blank
    0.39
     Blank
    0.35
     threw
    0.35
    "--
    0.34
     شهد
    0.34
     wide
    0.34
     indiscrimin
    0.34
    ToJson
    0.34
     everytime
    0.34
    Activations Density 0.041%

    No Known Activations