© 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. 117856
    Prev
    Next
    INDEX
    Explanations

    modified ROMs

    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
     داخل
    -0.07
     доступ
    -0.07
     subcut
    -0.07
     নতুন
    -0.07
     unsuspecting
    -0.07
     ненави
    -0.06
    Insufficient
    -0.06
     সফল
    -0.06
     직접
    -0.06
     جدید
    -0.06
    POSITIVE LOGITS
    ;
    0.06
    zé
    0.06
    .
    0.06
     extension
    0.06
     arresting
    0.05
     sculpted
    0.05
     levels
    0.05
    Following
    0.05
    .@
    0.05
     след
    0.05
    Activations Density 0.030%

    No Known Activations