© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1122
    Prev
    Next
    INDEX
    Explanations

    questions or statements immediately after

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

    publicly disclosed

    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
    ÉRI
    0.42
    觐
    0.41
    Moles
    0.40
    Poz
    0.40
    ێنی
    0.40
    لية
    0.39
    निया
    0.39
    Poisson
    0.39
    📖
    0.38
    Maxima
    0.38
    POSITIVE LOGITS
     Whose
    0.56
     whose
    0.46
     Would
    0.46
     Are
    0.45
     Does
    0.44
     Will
    0.43
     Your
    0.42
     Another
    0.42
     Anybody
    0.42
     Is
    0.42
    Activations Density 0.001%

    No Known Activations