© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2671
    Prev
    Next
    INDEX
    Explanations

    code completion following punctuation

    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_65k_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
    </h3>
    1.42
     ）
    1.14
    ']")
    1.12
    ]')
    1.07
    ）
    1.06
    ပါတယ်
    1.00
    "]},
    0.99
    "]')
    0.97
    '])
    0.97
    ')"
    0.96
    POSITIVE LOGITS
    ".
    4.43
    }.
    4.36
    “.
    4.24
    ”.
    4.17
    ].
    4.10
    `.
    4.09
    ).
    4.06
    ».
    4.05
    '.
    3.97
     ».
    3.81
    Activations Density 1.495%

    No Known Activations