Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8273
    Prev
    Next
    INDEX
    Explanations

    remembering or recalling

    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
    yok
    -0.77
    انیه
    -0.77
    сколь
    -0.75
    gapi
    -0.75
    рев
    -0.74
     selon
    -0.71
    refine
    -0.70
    orz
    -0.69
    isière
    -0.69
    lizia
    -0.68
    POSITIVE LOGITS
     remember
    8.00
     remembers
    6.78
    remember
    6.34
     remembered
    6.28
     Remember
    6.09
    Remember
    6.03
     remembering
    5.69
     recall
    5.56
     recalls
    4.56
     remembrance
    4.44
    Activations Density 0.191%

    No Known Activations