© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128543
    Prev
    Next
    INDEX
    Explanations

    academic and institutional affiliations

    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
     समस्याएं
    -0.07
     llegada
    -0.06
     സ്വാ
    -0.06
     همیشه
    -0.06
    同様
    -0.06
    によっては
    -0.06
     محم
    -0.06
     دائما
    -0.06
     to
    -0.06
    ები
    -0.06
    POSITIVE LOGITS
     býval
    0.06
     avoidable
    0.06
     erstwhile
    0.06
     திரும்ப
    0.06
     określ
    0.05
     öner
    0.05
    elwv
    0.05
     duas
    0.05
    ณิต
    0.05
     రెండు
    0.05
    Activations Density 0.001%

    No Known Activations