© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1475
    Prev
    Next
    INDEX
    Explanations

    key-value pair delimiter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_width_16k_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
    '></
    0.94
    "></
    0.93
    '>");
    0.93
    '>"
    0.91
    </blockquote>
    0.83
    "/></
    0.83
    '>"+
    0.83
    धियों
    0.80
    "/>
    0.76
    '/>
    0.76
    POSITIVE LOGITS
    】,
    3.85
    ),
    3.61
    },
    3.47
    .),
    3.26
    ),
    3.21
    ,),
    3.14
    ",
    3.11
    !),
    3.10
    ],
    3.08
     ),
    3.08
    Activations Density 0.603%

    No Known Activations