© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120795
    Prev
    Next
    INDEX
    Explanations

    quoting or enclosing context

    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
     while
    -0.06
     multimillion
    -0.06
     controversial
    -0.06
     billionaire
    -0.06
    varying
    -0.06
     variously
    -0.06
     famously
    -0.06
    рное
    -0.05
     infamous
    -0.05
     billion
    -0.05
    POSITIVE LOGITS
     only
    0.07
    來看
    0.07
    ദം
    0.06
    要把
    0.06
     bestimmte
    0.06
     einzigen
    0.06
    ត្
    0.06
     따라서
    0.06
     bestimmen
    0.06
    来看
    0.06
    Activations Density 0.006%

    No Known Activations