© 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. 129320
    Prev
    Next
    INDEX
    Explanations

    default values and versions

    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
     including
    -0.07
     här
    -0.06
     युवाओ
    -0.06
    ডিং
    -0.06
    <0xB4>
    -0.06
    ického
    -0.06
     other
    -0.06
    CommonAncestor
    -0.06
     άλλα
    -0.06
     illustrating
    -0.06
    POSITIVE LOGITS
    代わりに
    0.08
     대부분
    0.06
    Default
    0.06
    勝利
    0.06
     instead
    0.06
     tandis
    0.06
     invece
    0.06
     այդ
    0.05
     Utilize
    0.05
     Default
    0.05
    Activations Density 0.001%

    No Known Activations