© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7615
    Prev
    Next
    INDEX
    Explanations

    gifts for recipients and occasions

    np_acts-logits-general · gemini-2.5-flash-lite

    thoughtful gifts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     компенса
    0.41
    正常的
    0.39
    擅
    0.39
     conformément
    0.38
     reparation
    0.38
     えっと
    0.38
     plufieurs
    0.38
     грома
    0.38
     $\|\
    0.38
     wilfully
    0.37
    POSITIVE LOGITS
     recipient
    1.04
     recipients
    1.04
     birthdays
    1.02
     loved
    1.00
     thoughtful
    1.00
     thoughtfulness
    0.97
     Recipients
    0.94
    Recipient
    0.91
     Loved
    0.90
    recipient
    0.88
    Activations Density 0.272%

    No Known Activations