© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 50660
    Prev
    Next
    INDEX
    Explanations

    unique or only one

    np_acts-logits-general · gemini-2.5-flash-lite

    unique constraints and keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bouch
    0.45
    手动
    0.43
     đậm
    0.43
    Bună
    0.42
     tj
    0.42
     adhesions
    0.41
    渕
    0.41
    ɕ
    0.40
    රි
    0.40
     ফেরত
    0.40
    POSITIVE LOGITS
    UNIQUE
    0.78
     uniqueness
    0.75
    Unique
    0.66
     únicas
    0.63
    唯一
    0.60
     uniquely
    0.59
    unique
    0.57
     UNIQUE
    0.57
     unique
    0.57
     Unique
    0.55
    Activations Density 0.003%

    No Known Activations