© 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. 128842
    Prev
    Next
    INDEX
    Explanations

    Background, Marine, Aust, Q(

    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
    只有
    -0.08
    哪個
    -0.08
     einzigen
    -0.08
     które
    -0.07
     tylko
    -0.07
     الذي
    -0.07
     seules
    -0.07
     which
    -0.07
     only
    -0.07
     courier
    -0.07
    POSITIVE LOGITS
    ■
    0.06
    ,.
    0.06
    プラン
    0.06
     speckled
    0.05
    的
    0.05
     sast
    0.05
     productor
    0.05
     barbaric
    0.05
     disintegrated
    0.05
    renc
    0.05
    Activations Density 0.002%

    No Known Activations