© 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. 2109
    Prev
    Next
    INDEX
    Explanations

    real estate

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

    real-time or real-world

    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
     மிகவும்
    0.46
    referred
    0.43
     extremadamente
    0.41
     precisamente
    0.41
     매우
    0.41
     extremamente
    0.40
     estremamente
    0.39
    扃
    0.39
    ब्बे
    0.38
     Omphalodes
    0.38
    POSITIVE LOGITS
     estate
    1.19
    estate
    1.13
     ESTATE
    1.03
     Estate
    1.00
    Estate
    1.00
    iable
    0.92
    igned
    0.90
    isations
    0.89
    igning
    0.85
    politik
    0.83
    Activations Density 0.162%

    No Known Activations