© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3857
    Prev
    Next
    INDEX
    Explanations

    truth classifier

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

    boolean \"true\" values

    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
     പരിച
    0.37
    㓡
    0.35
     আশ্বাস
    0.34
    quinazolin
    0.34
    printStackTrace
    0.33
    പ്പെട്ട
    0.33
    ronidazole
    0.33
    薑
    0.33
    থিল
    0.32
    ającym
    0.32
    POSITIVE LOGITS
     true
    4.47
    true
    4.19
     True
    4.03
     TRUE
    4.03
    True
    3.97
    TRUE
    3.67
    真
    3.31
     verdadeiro
    3.25
     ट्रू
    3.20
     verdadera
    3.11
    Activations Density 0.194%

    No Known Activations