© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116178
    Prev
    Next
    INDEX
    Explanations

    use or I feel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Atem
    -0.06
     anhydride
    -0.06
     coincident
    -0.06
    albumin
    -0.06
     renegoti
    -0.06
    riya
    -0.06
     compatible
    -0.06
    jež
    -0.05
     manejar
    -0.05
     Autón
    -0.05
    POSITIVE LOGITS
     safety
    0.07
    helping
    0.06
     divided
    0.06
    safety
    0.06
     Safety
    0.06
    簡単
    0.06
     அளவு
    0.06
     vanishing
    0.06
     เขา
    0.06
     easy
    0.06
    Activations Density 0.048%

    No Known Activations