© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2453
    Prev
    Next
    INDEX
    Explanations

    protection and covering

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

    firewall and protection

    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_262k_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
     získ
    0.42
     szerző
    0.40
    .??.??"]
    0.39
     финанси
    0.39
     публі
    0.39
     frågor
    0.38
     jähr
    0.38
    仴
    0.38
     disponibilités
    0.38
     alfabet
    0.37
    POSITIVE LOGITS
     protecting
    1.16
     protects
    1.07
     protection
    1.05
     protective
    1.05
    protect
    1.04
     protect
    1.01
     shielding
    1.00
    保护
    0.97
    保護
    0.96
    防护
    0.95
    Activations Density 0.353%

    No Known Activations