© 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. 31-GEMMASCOPE-2-RES-16K
    7. 14532
    Prev
    Next
    INDEX
    Explanations

    privacy and secrets

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

    embarrassment and humiliation

    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_31_width_16k_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
    Responding
    0.45
    眄
    0.43
     inanimate
    0.42
    支援
    0.42
     qualifiers
    0.41
     ከአ
    0.41
     ভর
    0.40
    త్ప
    0.40
    依靠
    0.40
    輔
    0.40
    POSITIVE LOGITS
     secrecy
    1.42
     concealment
    1.15
     disclosure
    1.11
     secretive
    1.09
     concealing
    1.09
    秘密
    1.08
     비밀
    1.08
     confidentiality
    1.07
     secret
    1.05
     गोपनीयता
    1.05
    Activations Density 0.420%

    No Known Activations