© 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. 34-GEMMASCOPE-RES-131K
    7. 116317
    Prev
    Next
    INDEX
    Explanations

    various languages

    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
     proprietà
    -1.02
    ඈ
    -0.97
    obrá
    -0.96
    /"
    -0.96
     într
    -0.95
     шко
    -0.93
     miſ
    -0.93
    苤
    -0.91
    }$,
    -0.90
    䊉
    -0.89
    POSITIVE LOGITS
     сериала
    0.98
     zato
    0.96
    phylococcus
    0.94
     favourites
    0.88
    常见的
    0.88
    平和
    0.86
     schlagen
    0.85
    Ō
    0.85
     Teenage
    0.85
     दौर
    0.84
    Activations Density 0.897%

    No Known Activations