© 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. 119991
    Prev
    Next
    INDEX
    Explanations

    John Coltrane

    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
     and
    -0.07
     The
    -0.07
    The
    -0.06
    К
    -0.06
    Three
    -0.06
    Taking
    -0.06
    K
    -0.06
     ३
    -0.06
     the
    -0.06
    Here
    -0.05
    POSITIVE LOGITS
     уйнагыз
    0.07
     теркәлүсез
    0.07
    หรือ
    0.06
    ﹒
    0.06
     ayaa
    0.06
     صہیونیوں
    0.06
     findViewById
    0.06
    ปัจจุบัน
    0.06
     beetroot
    0.06
     samtid
    0.06
    Activations Density 0.018%

    No Known Activations