© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130587
    Prev
    Next
    INDEX
    Explanations

    float numbers

    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_22/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
    </b>
    -3.11
     verdaderamente
    -2.61
     Saltar
    -2.55
     exactamente
    -2.50
    TryDecode
    -2.34
     появились
    -2.30
     هناك
    -2.25
     alcuni
    -2.23
     algunas
    -2.16
     they
    -2.14
    POSITIVE LOGITS
    𓋼
    3.27
    </h3>
    2.75
    }
    2.69
    ]
    2.44
    婞
    2.36
    )
    2.20
     CascadeType
    2.19
    洐
    2.16
    {
    2.09
    泔
    2.08
    Activations Density 0.012%

    No Known Activations