© 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. 120487
    Prev
    Next
    INDEX
    Explanations

    transcriptions and lyrics

    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
    ent
    -0.06
    new
    -0.06
    orat
    -0.06
     religioso
    -0.06
     সভায়
    -0.06
    page
    -0.05
    select
    -0.05
     selected
    -0.05
    attributes
    -0.05
     പറഞ്ഞ
    -0.05
    POSITIVE LOGITS
     Sprache
    0.06
    USU
    0.06
     Dare
    0.06
    だよ
    0.06
    UpperCase
    0.06
    虚拟
    0.06
    以前
    0.06
    Dans
    0.06
     як
    0.06
    зяй
    0.06
    Activations Density 0.044%

    No Known Activations