© 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. 1564
    Prev
    Next
    INDEX
    Explanations

    reach or reaching

    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
    JHEP
    -0.88
     candidacy
    -0.84
    currentUser
    -0.81
    adé
    -0.75
    が広
    -0.75
    oraf
    -0.73
    piración
    -0.72
    onien
    -0.71
    接著
    -0.71
    ciato
    -0.71
    POSITIVE LOGITS
     reach
    6.81
     reached
    6.50
     reaching
    6.22
     reaches
    6.09
    Reach
    5.59
    reach
    5.53
     Reach
    5.47
    Reaching
    5.28
     Reaching
    5.22
    reaching
    5.03
    Activations Density 0.364%

    No Known Activations