© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60070
    Prev
    Next
    INDEX
    Explanations

    closing brackets and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Verpflich
    -1.23
    }}=\
    -1.21
     می‌تواند
    -1.20
     tatsäch
    -1.20
    }}(\
    -1.19
    })=\
    -1.13
     utterly
    -1.12
     actual
    -1.09
     same
    -1.08
     both
    -1.06
    POSITIVE LOGITS
    ]
    2.77
    )
    2.55
    }
    2.13
    </strong>
    1.88
    </i>
    1.70
    </b>
    1.68
    ],
    1.63
    </em>
    1.61
    </sup>
    1.54
    ,]
    1.48
    Activations Density 0.021%

    No Known Activations