© 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. 14307
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and specifications related to software and programming.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    used for

    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
    4
    0.70
    through
    0.69
    ।
    0.64
    ne
    0.62
    r
    0.61
     povas
    0.61
    viridis
    0.60
    ৬
    0.59
    using
    0.59
    this
    0.58
    POSITIVE LOGITS
     as
    0.91
     upang
    0.73
    ع
    0.70
     sparingly
    0.68
     for
    0.67
     để
    0.67
     when
    0.64
    fulness
    0.61
    ον
    0.59
     interchangeably
    0.58
    Activations Density 0.102%

    No Known Activations