© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 1697
    Prev
    Next
    INDEX
    Explanations

    brackets and placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    <start_of_image>
    1.27
    </h2>
    0.84
     Semoga
    0.64
     })}
    0.59
    surprise
    0.58
     surprise
    0.57
    <h2>
    0.57
    ')));
    0.56
    chill
    0.56
     Süden
    0.55
    POSITIVE LOGITS
    ]
    5.06
    ],
    4.79
    .]
    4.78
     ]
    4.50
    ].
    4.50
    ];
    4.48
    ]:
    4.47
    !]
    4.44
    ](
    4.31
    ]-
    4.30
    Activations Density 0.210%

    No Known Activations