© 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. 32096
    Prev
    Next
    INDEX
    Explanations

    heading into competition

    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
     kokos
    -0.74
     veramente
    -0.72
    plusplus
    -0.69
     termini
    -0.68
    υχ
    -0.67
    uploadFile
    -0.67
    rench
    -0.67
    去吧
    -0.67
    inbox
    -0.66
    ﻧ
    -0.66
    POSITIVE LOGITS
     heading
    5.44
    Heading
    4.13
     entering
    4.00
     Heading
    3.98
    heading
    3.92
     going
    3.92
     Entering
    3.20
    Entering
    3.17
     headed
    3.00
    entering
    3.00
    Activations Density 0.133%

    No Known Activations