© 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. 28976
    Prev
    Next
    INDEX
    Explanations

    LLMs limitations

    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
     wszyst
    0.47
    გნ
    0.46
    Pren
    0.45
     וי
    0.43
    镉
    0.41
     Holton
    0.40
    แล
    0.39
     سەر
    0.39
     випадку
    0.39
    改めて
    0.39
    POSITIVE LOGITS
     ఆది
    0.48
    ças
    0.47
    px
    0.46
    system
    0.43
    iterable
    0.43
    entity
    0.42
    bij
    0.42
    ü
    0.42
    ki
    0.41
    ie
    0.41
    Activations Density 0.002%

    No Known Activations