© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100615
    Prev
    Next
    INDEX
    Explanations

    means that

    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_10/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
    ',
    -2.56
    '
    -2.11
    </td>
    -2.09
    )
    -1.62
     remain
    -1.55
    #%%
    -1.52
    ",
    -1.51
    が
    -1.48
    }
    -1.46
     observe
    -1.45
    POSITIVE LOGITS
    摃
    1.99
     городе
    1.89
     the
    1.70
    ᜀ
    1.63
    豨
    1.62
    ῞
    1.61
     administrativa
    1.56
    筴
    1.55
    桕
    1.54
    另一方面
    1.52
    Activations Density 0.008%

    No Known Activations