© 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. 12571
    Prev
    Next
    INDEX
    Explanations

    year context

    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
    گران
    0.49
    Authenticated
    0.49
    ្
    0.46
    Duplicate
    0.45
    vrez
    0.45
    eliti
    0.45
     सशस्त्र
    0.44
    }}^{(\
    0.43
    䨪
    0.43
    Immutable
    0.42
    POSITIVE LOGITS
    例子
    0.43
    了一下
    0.36
     Oh
    0.35
     Aldi
    0.35
    缺失
    0.35
     البعض
    0.35
     annum
    0.35
     mentorship
    0.34
     seeker
    0.34
    ậc
    0.34
    Activations Density 0.001%

    No Known Activations