© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119264
    Prev
    Next
    INDEX
    Explanations

    suspected threats and anxieties

    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
     redan
    -0.06
     možda
    -0.06
    Binder
    -0.06
     നടത്തി
    -0.06
    already
    -0.06
    achers
    -0.06
    des
    -0.06
     forceful
    -0.06
     ક
    -0.06
     செய்து
    -0.06
    POSITIVE LOGITS
     paranoia
    0.07
     Fear
    0.07
     fear
    0.07
    谣
    0.06
     reassurance
    0.06
     medo
    0.06
     anxieties
    0.06
     fondos
    0.06
     fears
    0.06
     rumor
    0.06
    Activations Density 0.075%

    No Known Activations