© 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. 118395
    Prev
    Next
    INDEX
    Explanations

    necessity or requirement

    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
     trochę
    -0.06
     some
    -0.06
     khá
    -0.06
     rast
    -0.06
     bastante
    -0.06
    いたり
    -0.05
     delightfully
    -0.05
     ci
    -0.05
     नव्या
    -0.05
     बच
    -0.05
    POSITIVE LOGITS
     해야
    0.10
    必須
    0.09
    해야
    0.09
    需要
    0.09
     باید
    0.09
    必需
    0.09
     trebuie
    0.09
     должна
    0.08
     керек
    0.08
     нужно
    0.08
    Activations Density 0.028%

    No Known Activations