© 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. 116685
    Prev
    Next
    INDEX
    Explanations

    greater than or equal to

    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
     البريط
    -0.06
     リ
    -0.06
     तुम्हाला
    -0.06
     কোনো
    -0.06
     britannique
    -0.06
     wher
    -0.06
    assay
    -0.06
    ALLOW
    -0.06
     não
    -0.06
     tidak
    -0.06
    POSITIVE LOGITS
    ccs
    0.06
    ----------
    0.06
    -------------
    0.06
    Ux
    0.06
    changing
    0.06
     방법
    0.05
     affecting
    0.05
     해결
    0.05
     calcule
    0.05
    也不能
    0.05
    Activations Density 0.002%

    No Known Activations