© 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. 49012
    Prev
    Next
    INDEX
    Explanations

    html meta tags

    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
    それにしても
    -1.20
     campeón
    -1.16
     ordina
    -1.10
     pernic
    -1.09
    などを
    -1.06
     accessori
    -1.04
    についても
    -1.04
     nawet
    -1.03
    を
    -1.02
    鶿
    -1.02
    POSITIVE LOGITS
    },
    1.30
     metų
    1.27
    >(&
    1.24
    
    1.15
     pieniądze
    1.14
    cherichia
    1.13
    "},
    1.13
    </th>
    1.12
    の人に
    1.12
    久し
    1.10
    Activations Density 0.190%

    No Known Activations