© 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. 120159
    Prev
    Next
    INDEX
    Explanations

    referred to or called

    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
     ፓ
    -0.06
     esattamente
    -0.06
     precisely
    -0.06
    它
    -0.06
    正確
    -0.06
     durum
    -0.06
     періо
    -0.06
    ठान
    -0.06
    確保
    -0.06
     to
    -0.06
    POSITIVE LOGITS
    }{}
    0.06
    ‑
    0.06
     halved
    0.06
    К
    0.06
     rhymes
    0.06
     diminishes
    0.06
     многие
    0.06
     neste
    0.06
     wonderful
    0.06
     hacen
    0.05
    Activations Density 0.012%

    No Known Activations