© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106627
    Prev
    Next
    INDEX
    Explanations

    mathematical equation structures

    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
    ()),
    -0.91
     their
    -0.89
    their
    -0.85
    Their
    -0.84
     Savoie
    -0.83
     Gór
    -0.82
     Railway
    -0.80
    ône
    -0.80
    년
    -0.80
     salon
    -0.79
    POSITIVE LOGITS
     Manufact
    0.88
    }$
    0.84
     Passo
    0.82
     PUC
    0.81
     ALC
    0.79
    }
    0.79
     Multicultural
    0.78
     Hashtag
    0.77
     学習
    0.77
     chống
    0.76
    Activations Density 0.002%

    No Known Activations