© 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. 129260
    Prev
    Next
    INDEX
    Explanations

    not followed by contrast

    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
     također
    -0.08
     hoặc
    -0.07
     또는
    -0.07
     also
    -0.07
     också
    -0.07
     también
    -0.07
     também
    -0.07
     cũng
    -0.07
     ასევე
    -0.07
     наличие
    -0.07
    POSITIVE LOGITS
     இந்த
    0.06
     this
    0.06
     dieser
    0.06
    asure
    0.06
     dieses
    0.06
    THIS
    0.05
     এই
    0.05
     aceste
    0.05
     diesem
    0.05
    This
    0.05
    Activations Density 0.008%

    No Known Activations