© 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. 120282
    Prev
    Next
    INDEX
    Explanations

    ( dynamically)

    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
     in
    -0.09
     a
    -0.08
     an
    -0.08
     numerous
    -0.07
     excellent
    -0.07
     zahlreichen
    -0.07
     jednym
    -0.06
     splendid
    -0.06
     this
    -0.06
     одним
    -0.06
    POSITIVE LOGITS
     остальные
    0.06
    normally
    0.06
    proofing
    0.06
     counterpart
    0.06
     pozosta
    0.06
     बहुतेक
    0.06
     seldom
    0.06
     jego
    0.06
    看不到
    0.06
     illustrates
    0.05
    Activations Density 0.003%

    No Known Activations