© 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. 117218
    Prev
    Next
    INDEX
    Explanations

    C++ function/template issues

    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
    𝘬
    -0.06
     begon
    -0.06
    ਸ਼
    -0.06
    لف
    -0.06
     wundersch
    -0.06
    碰撞
    -0.06
     inizia
    -0.06
    最短
    -0.06
     exclusivement
    -0.06
     cocina
    -0.06
    POSITIVE LOGITS
     defunct
    0.06
     amends
    0.06
    moving
    0.06
     orphan
    0.06
     subunit
    0.06
    advanced
    0.05
     지원
    0.05
     solitary
    0.05
     dysfunctional
    0.05
     Zoological
    0.05
    Activations Density 0.005%

    No Known Activations