© 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. 119192
    Prev
    Next
    INDEX
    Explanations

    promising or potential outcomes

    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
    ilerini
    -0.07
    金额
    -0.07
    commend
    -0.07
    isinin
    -0.07
    改めて
    -0.06
     siguió
    -0.06
     safest
    -0.06
     inhib
    -0.06
    Analy
    -0.06
     prefers
    -0.06
    POSITIVE LOGITS
     promises
    0.06
     promising
    0.06
     utterance
    0.06
     looks
    0.06
     önces
    0.06
     will
    0.06
    Before
    0.06
     ayam
    0.06
    mPreview
    0.05
     vermutlich
    0.05
    Activations Density 0.030%

    No Known Activations