© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 14550
    Prev
    Next
    INDEX
    Explanations

    doctoral dissertation or thesis

    np_acts-logits-general · gemini-2.5-flash-lite

    https://

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    రుగులు
    0.42
     mı
    0.42
     sediment
    0.41
    槭
    0.40
    )}$.
    0.39
    кономі
    0.39
    Джек
    0.39
    ))=\
    0.38
    ەر
    0.38
    )=(-
    0.38
    POSITIVE LOGITS
    !]
    1.04
    ()]
    0.95
    ],
    0.94
    ];
    0.86
    ].
    0.85
    ”]
    0.85
    ]
    0.84
    .]
    0.84
    ?]
    0.84
    ,]
    0.82
    Activations Density 0.026%

    No Known Activations