© 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. 128998
    Prev
    Next
    INDEX
    Explanations

    nerd, geek, awkward

    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
    ams
    -0.06
     Nonetheless
    -0.06
     proportionality
    -0.06
     निष्
    -0.06
     hoax
    -0.06
    🔞
    -0.06
     অনেক
    -0.06
     registered
    -0.06
     πλα
    -0.06
     presc
    -0.06
    POSITIVE LOGITS
     minat
    0.06
     Preparation
    0.06
    ంచరీలు
    0.06
    Preparation
    0.06
    libr
    0.06
     vestido
    0.05
    ｋ
    0.05
     BEFORE
    0.05
     nerdy
    0.05
     생활
    0.05
    Activations Density 0.012%

    No Known Activations