© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109721
    Prev
    Next
    INDEX
    Explanations

    remember something

    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
     wohin
    -1.02
    когда
    -0.98
    сколько
    -0.95
     perché
    -0.94
     flera
    -0.84
     beinahe
    -0.84
     more
    -0.84
     cocinas
    -0.84
     few
    -0.84
     Потому
    -0.84
    POSITIVE LOGITS
    Remember
    1.40
     remember
    1.39
    remember
    1.38
     something
    1.27
    Something
    1.25
     Remember
    1.20
    something
    1.19
     obviously
    1.16
    obviously
    1.13
    Bearing
    1.12
    Activations Density 0.017%

    No Known Activations