© 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-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-16K
    4. 803
    Prev
    Next
    INDEX
    Explanations

    http links to resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     output
    0.77
     cheese
    0.74
    鎗
    0.71
     complicating
    0.71
     somatic
    0.70
     ExifInterface
    0.69
     kişinin
    0.69
     krem
    0.69
     输出
    0.68
     simplify
    0.68
    POSITIVE LOGITS
     ]
    1.47
    ](
    1.40
    .]
    1.40
     ])
    1.39
    ])
    1.38
     ].
    1.35
    -]
    1.30
     ],
    1.29
    ()]
    1.26
    ]")
    1.21
    Activations Density 0.057%

    No Known Activations