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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6780
    Prev
    Next
    INDEX
    Explanations

    you following decisions or outcomes

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

    are a few drafts

    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
    xi
    0.48
    ing
    0.44
    mon
    0.44
    _
    0.44
    7
    0.42
    8
    0.42
    ochond
    0.42
    kh
    0.41
    oi
    0.41
    ên
    0.40
    POSITIVE LOGITS
    ⺈
    0.44
    ‍♂
    0.44
     テ
    0.44
     COW
    0.43
     personel
    0.43
    hellip
    0.40
     সমু
    0.40
     የግ
    0.40
    $-$,
    0.39
     WEATHER
    0.39
    Activations Density 0.175%

    No Known Activations