© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3301
    Prev
    Next
    INDEX
    Explanations

    topics and options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    ↵↵
    2.63
    }
    2.44
    】
    2.39
    ].
    2.39
    Conclusion
    2.38
    }]
    2.37
    ]
    2.36
    ]".
    2.32
    .]
    2.31
     ]
    2.30
    POSITIVE LOGITS
    一方面
    1.18
     oftentimes
    1.18
    いくつか
    1.05
     متش
    1.03
    在前
    1.02
     whenever
    1.01
     ranging
    0.99
    bě
    0.98
     many
    0.98
    何度
    0.97
    Activations Density 1.087%

    No Known Activations