© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47389
    Prev
    Next
    INDEX
    Explanations

    checkpoint, waypoint, breakpoint markers

    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
    áld
    -0.80
    ляли
    -0.77
     праздни
    -0.77
    puerto
    -0.73
     preface
    -0.71
    DIRECT
    -0.70
    がい
    -0.70
    Permutation
    -0.69
    motive
    -0.69
    oplasma
    -0.69
    POSITIVE LOGITS
     checkpoint
    2.67
     checkpoints
    2.45
    checkpoint
    2.08
     Checkpoint
    2.02
    Checkpoint
    1.74
     waypoint
    1.47
     breakpoint
    1.46
     points
    1.41
     point
    1.30
     точки
    1.30
    Activations Density 0.040%

    No Known Activations