© 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. 55988
    Prev
    Next
    INDEX
    Explanations

    block access

    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
    los
    0.64
    >
    0.55
    l
    0.55
    v
    0.54
    lst
    0.53
    list
    0.53
    g
    0.47
    okus
    0.47
    wald
    0.46
    lista
    0.46
    POSITIVE LOGITS
    鍮
    0.46
    㭋
    0.46
     bâtiments
    0.45
     Offices
    0.45
    ଚ
    0.44
    抟
    0.44
     चतुर्थ
    0.43
     lanjutkan
    0.43
     contractual
    0.43
     droits
    0.43
    Activations Density 0.006%

    No Known Activations