© 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. 28836
    Prev
    Next
    INDEX
    Explanations

    official terms and documents

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

    bacteria, viruses, or ulcers

    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
    빤
    0.45
     Borel
    0.44
     seguenti
    0.43
     ..$
    0.43
     Quil
    0.42
     agregó
    0.42
     buddhav
    0.42
     بکر
    0.42
     وو
    0.41
    헷
    0.41
    POSITIVE LOGITS
    到来
    0.40
     detected
    0.39
     r
    0.39
    กีฬา
    0.38
    之中
    0.38
    MediaPath
    0.38
     ebb
    0.37
    之下
    0.37
     চলার
    0.37
    業務用
    0.36
    Activations Density 0.000%

    No Known Activations