© 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
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8970
    Prev
    Next
    INDEX
    Explanations

    fine-tuning URLs

    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_22_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
    </blockquote>
    4.21
    ].
    2.98
    .].
    2.84
    ]。
    2.81
    ].”
    2.79
     ].
    2.69
    '].
    2.68
    ]".
    2.66
    ]$.
    2.61
    ]."
    2.55
    POSITIVE LOGITS
    </th>
    3.58
    </h2>
    3.48
    』
    3.35
    </u>
    3.01
    </a>
    2.62
    】,
    2.53
    </h5>
    2.52
    ),"
    2.51
    "),
    2.43
    ,"
    2.42
    Activations Density 0.226%

    No Known Activations