© 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. 116517
    Prev
    Next
    INDEX
    Explanations

    porn and masturbation content

    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
     tonight
    -0.07
     сегодня
    -0.07
     لهذه
    -0.07
    jesi
    -0.07
     אני
    -0.07
     vervolgens
    -0.07
     необы
    -0.06
     сегодняшний
    -0.06
     Einwill
    -0.06
     inoltre
    -0.06
    POSITIVE LOGITS
     but
    0.06
    <b>
    0.06
     released
    0.06
    <h1>
    0.06
     niezbęd
    0.06
     Gérard
    0.06
    <strong>
    0.06
     specialization
    0.06
     leg
    0.05
    ολ
    0.05
    Activations Density 0.033%

    No Known Activations