© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6738
    Prev
    Next
    INDEX
    Explanations

    2 3

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

    locking and unlocking

    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_53_width_65k_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
    matrices
    0.43
    sam
    0.41
    rake
    0.41
     equips
    0.40
    пия
    0.40
    빠
    0.39
     sõ
    0.38
    consistency
    0.38
     পো
    0.37
     横
    0.37
    POSITIVE LOGITS
     locked
    0.64
     Locked
    0.56
     LOCKED
    0.54
    Locked
    0.47
     denying
    0.47
    illary
    0.44
     deny
    0.44
     Hone
    0.43
     volcan
    0.42
     stormed
    0.42
    Activations Density 0.000%

    No Known Activations