© 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. 130361
    Prev
    Next
    INDEX
    Explanations

    accessing Microsoft Graph API

    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
     humanoid
    -0.06
     Robo
    -0.05
    त्तियों
    -0.05
     दक्षिणी
    -0.05
    wheeler
    -0.05
     fork
    -0.05
     অঞ্চ
    -0.05
    习惯
    -0.05
     স্ম
    -0.05
     Förder
    -0.05
    POSITIVE LOGITS
     any
    0.07
    viable
    0.07
     நாங்கள்
    0.06
    ૂર
    0.06
    いくつか
    0.06
    users
    0.06
     some
    0.06
     dek
    0.06
     저희
    0.06
    tem
    0.06
    Activations Density 0.006%

    No Known Activations