© 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. 1104
    Prev
    Next
    INDEX
    Explanations

    exhibits signal or pattern

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

    tends to behave

    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
     quieran
    0.60
     хотят
    0.58
    让你
    0.55
    菈
    0.54
    Sadly
    0.54
     gedaan
    0.53
    Wouldn
    0.53
     मकसद
    0.52
     చేస్తున్నారు
    0.52
    鹜
    0.52
    POSITIVE LOGITS
     exhibit
    1.51
     exhibits
    1.47
     behaves
    1.27
     exhibited
    1.23
     possesses
    1.21
     behave
    1.16
     undergoes
    1.16
     undergo
    1.13
     exhib
    1.12
     differs
    1.11
    Activations Density 0.469%

    No Known Activations