© 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. 41426
    Prev
    Next
    INDEX
    Explanations

    persistence, remain active

    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
    ysł
    0.51
     emphasises
    0.45
     રૂપિયા
    0.45
    intis
    0.45
    mber
    0.43
     emphasise
    0.43
    =\{
    0.43
    മ്ബ
    0.43
     comien
    0.42
     totalled
    0.42
    POSITIVE LOGITS
    ة
    0.45
    ،
    0.45
     _
    0.45
     Omn
    0.44
     Harry
    0.44
     UCI
    0.44
    uvi
    0.42
    ०
    0.42
     Kenny
    0.42
     Sheep
    0.42
    Activations Density 0.002%

    No Known Activations