© 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. 91122
    Prev
    Next
    INDEX
    Explanations

    lock or unlock

    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
     reproductor
    -0.84
     получить
    -0.79
     complicate
    -0.76
    купа
    -0.75
     Yesterday
    -0.72
    denes
    -0.71
     Widow
    -0.71
    关心
    -0.70
    Dete
    -0.69
     muhimu
    -0.67
    POSITIVE LOGITS
    Lock
    1.69
     lock
    1.57
     Lock
    1.52
    LOCK
    1.44
     LOCK
    1.42
    lock
    1.41
     locks
    1.33
     Unlock
    1.33
    Unlock
    1.32
    unlocked
    1.30
    Activations Density 0.020%

    No Known Activations