© 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. 71954
    Prev
    Next
    INDEX
    Explanations

    describing further details

    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
     cucumber
    0.46
     Cucumber
    0.45
     destacar
    0.45
     administra
    0.44
    ät
    0.44
    𝙖
    0.44
     handleError
    0.43
     rekao
    0.43
     hvad
    0.43
     lanzó
    0.43
    POSITIVE LOGITS
    ggbb
    0.48
    situ
    0.47
    ganggu
    0.47
    giphy
    0.45
    lessness
    0.44
    FIA
    0.44
    䡉
    0.43
    g
    0.42
    エ
    0.42
    Շ
    0.42
    Activations Density 0.002%

    No Known Activations