© 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. 4075
    Prev
    Next
    INDEX
    Explanations

    dishonest vile cowardly disgusting vicious

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

    frivolous vanity and excess

    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
     воспринима
    0.59
     Perception
    0.51
     percib
    0.49
     empathetic
    0.48
     perceived
    0.48
     perceives
    0.47
     perception
    0.47
    憩
    0.47
     percepción
    0.46
     sensiblement
    0.46
    POSITIVE LOGITS
     dishonest
    0.84
     vile
    0.83
     cowardly
    0.82
     disgusting
    0.80
     vicious
    0.78
     coward
    0.77
     hypocrisy
    0.77
     sord
    0.77
     hypoc
    0.75
     vulgar
    0.75
    Activations Density 0.080%

    No Known Activations