© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130078
    Prev
    Next
    INDEX
    Explanations

    Brook Houghton

    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
     automatically
    -0.07
     விருப்ப
    -0.06
     cứ
    -0.06
    absorption
    -0.06
    Rg
    -0.06
    ड़ों
    -0.06
     IGN
    -0.06
     trasmissione
    -0.06
     idol
    -0.06
     Kız
    -0.06
    POSITIVE LOGITS
    华人
    0.07
     différente
    0.06
    μένων
    0.06
    Each
    0.06
    各自
    0.06
    它是
    0.06
     présents
    0.06
     différents
    0.06
    異なる
    0.06
    各有
    0.06
    Activations Density 0.034%

    No Known Activations