© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 19803
    Prev
    Next
    INDEX
    Explanations

    political freedom and encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     as
    0.48
    ])
    0.48
    ifice
    0.48
    n
    0.47
    ö
    0.46
    ä
    0.46
    isten
    0.46
    ]
    0.46
    r
    0.46
    inio
    0.45
    POSITIVE LOGITS
    䟧
    0.47
    বলে
    0.42
    ମ୍
    0.42
    مر
    0.41
     articoli
    0.41
    ন্যবাদ
    0.41
    addressed
    0.41
    新聞
    0.40
     enthalpies
    0.40
    ত্তর
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.