© 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. 60106
    Prev
    Next
    INDEX
    Explanations

    code comments describe actions

    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
     verdura
    -1.15
     suporta
    -1.11
     masaj
    -1.09
     its
    -1.09
     Ficha
    -1.05
     eleva
    -1.04
    囁
    -1.01
     moneda
    -0.99
     gimnas
    -0.99
     mascota
    -0.98
    POSITIVE LOGITS
     This
    1.18
     @
    1.12
    ~~~
    1.04
    }]$
    1.01
    oooo
    1.01
    </em>
    1.01
     THE
    1.00
    %
    0.97
     You
    0.96
    ####
    0.96
    Activations Density 0.005%

    No Known Activations