© 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. 814
    Prev
    Next
    INDEX
    Explanations

    Fuel type

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

    modelmultilingual direct answers

    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
    നെയും
    0.48
    azir
    0.43
     dispersions
    0.42
    িয়েত
    0.41
    IDAE
    0.41
    ]},
    0.40
    вець
    0.39
    ">/</
    0.39
    itekt
    0.38
    ندو
    0.38
    POSITIVE LOGITS
     \;
    0.68
     ){
    0.60
     }"
    0.58
     $$
    0.57
     \\\
    0.54
     }
    0.54
     \,\
    0.52
     }$
    0.51
     )\
    0.50
    textit
    0.50
    Activations Density 0.000%

    No Known Activations