© 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. 20386
    Prev
    Next
    INDEX
    Explanations

    configuration, conf, conference

    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
     are
    0.74
    ς
    0.63
     οποίος
    0.62
     )}
    0.61
    coroutines
    0.58
    œuvre
    0.57
     inwoners
    0.57
    癤
    0.55
    ેચ્છ
    0.53
     едно
    0.53
    POSITIVE LOGITS
    Conf
    1.00
     conf
    0.91
     CONF
    0.89
     Conf
    0.87
    is
    0.84
    >
    0.82
    し
    0.81
     Configur
    0.79
    ou
    0.79
     Configurations
    0.77
    Activations Density 0.051%

    No Known Activations