© 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. 7512
    Prev
    Next
    INDEX
    Explanations

    numbers and years

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

    years and estimates

    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
    tokenId
    0.36
    SizeMode
    0.35
    shorts
    0.34
    পুরে
    0.33
     เรีย
    0.33
    groupId
    0.33
    Iam
    0.33
    rowski
    0.33
    ociazione
    0.33
    शय
    0.33
    POSITIVE LOGITS
     २०१
    1.53
    今年的
    1.53
     ২০১৫
    1.51
     ২০১১
    1.50
     ১৯৯
    1.49
     ২০১০
    1.49
     ২০১৮
    1.48
     ۲۰۱
    1.48
     ২০১৭
    1.46
     ২০১৬
    1.46
    Activations Density 0.114%

    No Known Activations