© 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. 120467
    Prev
    Next
    INDEX
    Explanations

    license information

    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
     with
    -0.06
     самому
    -0.06
     itself
    -0.06
    jen
    -0.06
    with
    -0.06
    With
    -0.06
    )&=
    -0.06
    ળા
    -0.05
    原来
    -0.05
    ড্রিম
    -0.05
    POSITIVE LOGITS
    <0xC2>
    0.07
     രാജ്യ
    0.06
     unserer
    0.06
     our
    0.06
     abbiamo
    0.06
     även
    0.06
     computing
    0.06
    কের
    0.06
     we
    0.05
     Computing
    0.05
    Activations Density 0.008%

    No Known Activations