© 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. 129728
    Prev
    Next
    INDEX
    Explanations

    .ToString() calls

    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
     (
    -0.06
     რამდენ
    -0.06
     हमेशा
    -0.06
     multig
    -0.05
     at
    -0.05
     שלנו
    -0.05
     straks
    -0.05
     with
    -0.05
    或者
    -0.05
     で
    -0.05
    POSITIVE LOGITS
    ………..
    0.07
     ihn
    0.07
    ……….
    0.06
    ………….
    0.06
     आणि
    0.06
    และ
    0.06
     मकसद
    0.06
     যাওয়া
    0.06
    水的
    0.06
     আৰু
    0.06
    Activations Density 0.006%

    No Known Activations