© 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. 31-GEMMASCOPE-2-RES-16K
    7. 115
    Prev
    Next
    INDEX
    Explanations

    adverbial suffixes and words like owning

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

    focusing on specific aspects

    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_31_width_16k_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
    А
    0.78
    О
    0.74
    К
    0.69
    С
    0.64
    Х
    0.63
    До
    0.63
    Де
    0.61
    о
    0.60
    Г
    0.59
    Пу
    0.58
    POSITIVE LOGITS
     analyser
    0.57
     thisobject
    0.57
     heer
    0.55
     flavour
    0.54
     gate
    0.54
     senescence
    0.54
     perturbations
    0.53
     alertness
    0.53
     sulphide
    0.53
     vowel
    0.52
    Activations Density 0.001%

    No Known Activations