© 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. 130551
    Prev
    Next
    INDEX
    Explanations

    after/as/when/unlike + noun phrase

    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
     combustible
    -0.06
     obnoxious
    -0.06
    xes
    -0.06
     bitrate
    -0.06
     justiciable
    -0.06
     जिसमें
    -0.06
    eseen
    -0.06
    his
    -0.06
    主播
    -0.06
     Responder
    -0.05
    POSITIVE LOGITS
     will
    0.12
     would
    0.10
     can
    0.09
     sẽ
    0.08
     did
    0.08
     could
    0.08
     cannot
    0.08
     has
    0.08
     may
    0.08
     अपना
    0.08
    Activations Density 0.040%

    No Known Activations