© 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. 33844
    Prev
    Next
    INDEX
    Explanations

    state of being set

    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
     has
    -1.13
    /
    -1.05
    ous
    -1.01
    卫生间
    -0.99
    Према
    -0.93
    retries
    -0.91
    阳台
    -0.90
     without
    -0.89
     or
    -0.86
    bleven
    -0.86
    POSITIVE LOGITS
     that
    1.30
     که
    1.07
     jotka
    1.06
    ÜR
    0.97
     which
    0.94
     који
    0.94
    — 
    0.92
     artistique
    0.91
     étag
    0.90
     barva
    0.89
    Activations Density 0.064%

    No Known Activations