© 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. 59177
    Prev
    Next
    INDEX
    Explanations

    words followed by names or specific terms

    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
     pauvre
    -0.87
    𝐺
    -0.86
    師
    -0.82
     guapo
    -0.81
    ksiä
    -0.81
    IZAR
    -0.81
    leaved
    -0.79
    competent
    -0.78
     montanha
    -0.78
     云
    -0.77
    POSITIVE LOGITS
     Dallas
    0.95
    Dallas
    0.88
    DataMember
    0.88
     كرة
    0.84
     Cowboys
    0.81
     pecan
    0.79
     Emit
    0.77
     Infe
    0.76
    Texas
    0.76
    </tbody>
    0.76
    Activations Density 0.004%

    No Known Activations