© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59251
    Prev
    Next
    INDEX
    Explanations

    leaving their, saving the, spending much

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     there
    -1.21
     until
    -1.08
     scenery
    -1.03
     you
    -1.00
     weighting
    -0.95
     которая
    -0.93
     that
    -0.92
    ার
    -0.92
     ponieważ
    -0.91
    眺め
    -0.90
    POSITIVE LOGITS
    বহ
    1.13
     cirka
    1.09
     the
    1.05
     adatok
    1.04
     utmost
    1.03
     atleast
    1.03
     majorité
    0.99
     minut
    0.98
    Luego
    0.98
     âme
    0.98
    Activations Density 0.090%

    No Known Activations