© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 119239
    Prev
    Next
    INDEX
    Explanations

    programming code and descriptions

    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
     in
    -1.17
     to
    -1.16
     for
    -1.06
    +}$
    -1.00
     on
    -0.99
    izioni
    -0.99
     Every
    -0.94
     so
    -0.94
     and
    -0.92
    ๔
    -0.91
    POSITIVE LOGITS
     dreamstime
    1.05
     crappy
    1.03
     tumultuous
    1.02
     shimmering
    1.00
     extremely
    1.00
     powerpoint
    1.00
     vectorstock
    0.99
     USES
    0.98
     festge
    0.98
     Phila
    0.96
    Activations Density 0.000%

    No Known Activations